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

    Neuronpedia

    INDEX
    Explanations

    optimization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    发现
    -0.07
     imageNamed
    -0.07
    aman
    -0.06
    gets
    -0.06
    .trans
    -0.06
     kanı
    -0.06
    机场
    -0.06
     вп
    -0.06
    娘
    -0.06
    цієн
    -0.06
    POSITIVE LOGITS
    -process
    0.07
     altered
    0.06
    odial
    0.06
     numOf
    0.06
    .NULL
    0.06
     defStyle
    0.06
     иде
    0.06
    .cljs
    0.06
    _past
    0.06
    Trim
    0.06
    Act Density 0.008%

    No Known Activations