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

    Neuronpedia

    INDEX
    Explanations

    coding/scripting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Diagram
    -0.07
    27
    -0.07
    28
    -0.06
     vision
    -0.06
     kone
    -0.06
    Arena
    -0.06
    Options
    -0.06
    ((&
    -0.06
     bow
    -0.06
     utterly
    -0.06
    POSITIVE LOGITS
    .gold
    0.08
    一緒
    0.06
    _BLE
    0.06
     المخت
    0.06
    .IsValid
    0.06
    силь
    0.06
    staticmethod
    0.06
    /dataTables
    0.06
    ::::::::::::::::::::::::::::::::
    0.06
    .css
    0.06
    Act Density 0.031%

    No Known Activations