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

    Neuronpedia

    INDEX
    Explanations

    Operation instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :green
    -0.07
    (bc
    -0.07
    .Env
    -0.07
    .Tween
    -0.07
    .App
    -0.07
     Monkey
    -0.07
    _Var
    -0.07
    .backend
    -0.07
    .direct
    -0.06
    occer
    -0.06
    POSITIVE LOGITS
    -card
    0.07
    举报
    0.07
     proposition
    0.06
                    ↵↵
    0.06
     иде
    0.06
    客气
    0.06
    解決
    0.06
    ערוץ
    0.06
     הילד
    0.06
    쿳
    0.06
    Act Density 0.021%

    No Known Activations