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

    Neuronpedia

    INDEX
    Explanations

    Movie box office results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interventions
    -0.06
    ']));↵
    -0.06
    .weapon
    -0.06
    _ln
    -0.06
     phiên
    -0.06
    GetString
    -0.06
    ona
    -0.06
     hotspot
    -0.06
    capt
    -0.06
     bath
    -0.06
    POSITIVE LOGITS
    =cv
    0.06
    buttons
    0.06
    знача
    0.06
    搭
    0.06
     ΣΤ
    0.06
    ,Th
    0.06
     господар
    0.06
     quar
    0.06
     男
    0.06
     згідно
    0.06
    Act Density 0.021%

    No Known Activations