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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     محصول
    -0.07
     wrapper
    -0.07
    änder
    -0.07
     слож
    -0.06
     název
    -0.06
    vod
    -0.06
    .TextImageRelation
    -0.06
     deadlock
    -0.06
     wildcard
    -0.06
    proxy
    -0.06
    POSITIVE LOGITS
     انتظ
    0.07
    urat
    0.06
    rbrace
    0.06
    functional
    0.06
    册
    0.06
    reasonable
    0.06
    暗
    0.06
    คำ
    0.06
    هل
    0.06
     tuner
    0.06
    Act Density 0.011%

    No Known Activations