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

    Neuronpedia

    INDEX
    Explanations

    involved

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disappe
    -0.08
     disg
    -0.08
    护卫
    -0.07
     אלף
    -0.07
     WINDOWS
    -0.07
    各个方面
    -0.07
    嗄
    -0.07
    撵
    -0.07
    سرط
    -0.07
    旆
    -0.07
    POSITIVE LOGITS
     involved
    0.09
    оя
    0.07
    bv
    0.07
     Nz
    0.07
    inv
    0.07
    *pow
    0.06
    /div
    0.06
    pol
    0.06
    лив
    0.06
    _diag
    0.06
    Act Density 0.036%

    No Known Activations