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

    Neuronpedia

    INDEX
    Explanations

    negation

    np_max-act · gemini-2.0-flash

    The neuron broadly responds to medium-frequency content words (i.e. non-stopwords with real lexical meaning), regardless of part of speech.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    MOOTH
    -0.07
    omm
    -0.07
     problematic
    -0.07
     Zy
    -0.06
     destino
    -0.06
     nap
    -0.06
     vul
    -0.06
     questo
    -0.06
     descri
    -0.06
    'aff
    -0.06
    POSITIVE LOGITS
     dağ
    0.07
    _tcp
    0.06
    带
    0.06
     responder
    0.06
     kuruluş
    0.06
    +b
    0.06
    ्षमत
    0.06
     đau
    0.06
    ляться
    0.06
    ोज
    0.06
    Act Density 0.041%

    No Known Activations