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

    Neuronpedia

    INDEX
    Explanations

    Grammar and descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ib
    -0.07
     scattered
    -0.07
     Grab
    -0.07
    _stub
    -0.06
    Deferred
    -0.06
    FP
    -0.06
    Hur
    -0.06
    ··
    -0.06
    entialAction
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    러리
    0.07
    eldon
    0.06
    metatable
    0.06
    =logging
    0.06
     소리
    0.06
     empowered
    0.06
     rms
    0.06
    初始化
    0.05
    シア
    0.05
     tây
    0.05
    Act Density 0.165%

    No Known Activations