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

    Neuronpedia

    INDEX
    Explanations

    review

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cheap
    -0.07
     blockbuster
    -0.07
    Following
    -0.06
     anglais
    -0.06
    _k
    -0.06
     Subscription
    -0.06
    куп
    -0.06
    _le
    -0.06
     Ain
    -0.06
     lows
    -0.06
    POSITIVE LOGITS
     engraved
    0.07
    ’aut
    0.07
    (batch
    0.07
    /Graphics
    0.06
     freopen
    0.06
     Вс
    0.06
     collage
    0.06
     kapat
    0.06
     Profiles
    0.06
    σματα
    0.06
    Act Density 0.065%

    No Known Activations