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

    Neuronpedia

    INDEX
    Explanations

    bar charts code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     predicting
    -0.07
     dysfunctional
    -0.06
    zing
    -0.06
    िक
    -0.06
    區
    -0.06
    avs
    -0.06
    .fm
    -0.06
     deposition
    -0.06
    ladım
    -0.06
    фектив
    -0.06
    POSITIVE LOGITS
     NK
    0.06
    ;j
    0.06
     flesh
    0.06
    (Runtime
    0.06
    /J
    0.06
    ylan
    0.06
    /mp
    0.06
     neu
    0.06
     �
    0.06
    entifier
    0.06
    Act Density 0.026%

    No Known Activations