Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    political news/opinions

    np_max-act · gemini-2.0-flash

    phrases that express criticism or discontent towards political figures and policies.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron primarily picks out numeric expressions and quantifiable data (numbers, percentages, measurements) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     fusion
    -0.07
     AppCompatActivity
    -0.07
     مو
    -0.06
    _tm
    -0.06
     Colon
    -0.06
     NT
    -0.06
     polish
    -0.06
    ivityManager
    -0.06
    NT
    -0.06
     Anthem
    -0.06
    POSITIVE LOGITS
     stránky
    0.06
     nisi
    0.06
    .geometry
    0.06
     gefunden
    0.06
     inkl
    0.06
     pacman
    0.06
    .edge
    0.06
     Vine
    0.06
    Sr
    0.06
    �
    0.06
    Act Density 0.114%

    No Known Activations