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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literals in code (especially floating-point constants).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    청
    -0.07
     رع
    -0.06
     apoptosis
    -0.06
    _SECURITY
    -0.06
     umbrella
    -0.06
    uish
    -0.06
    (enc
    -0.06
     Patrol
    -0.06
     Municip
    -0.06
     Alumni
    -0.06
    POSITIVE LOGITS
    ス
    0.07
    -best
    0.06
    -hard
    0.06
     angled
    0.06
    ț
    0.06
     selectedIndex
    0.06
    ffmpeg
    0.06
     ší
    0.06
    aç
    0.06
    .Put
    0.06
    Act Density 0.082%

    No Known Activations