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

    Neuronpedia

    INDEX
    Explanations

    pursuant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     heaters
    -0.07
    _PUSH
    -0.07
     selects
    -0.07
    aghetti
    -0.07
    .shows
    -0.06
    �
    -0.06
    aptive
    -0.06
     Hollywood
    -0.06
    _dep
    -0.06
     Bethesda
    -0.06
    POSITIVE LOGITS
     диагности
    0.08
     BODY
    0.06
    ород
    0.06
     uvědom
    0.06
    ّم
    0.06
    �
    0.06
    acaktır
    0.06
    .Util
    0.06
     пре
    0.06
     lectures
    0.06
    Act Density 0.003%

    No Known Activations