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

    Neuronpedia

    INDEX
    Explanations

    say "System"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Населення
    -0.07
    Rails
    -0.07
    finance
    -0.06
     bloginfo
    -0.06
    貨
    -0.06
     theano
    -0.06
     Велик
    -0.06
    .locale
    -0.06
    ยวก
    -0.06
     billionaires
    -0.06
    POSITIVE LOGITS
    metros
    0.06
    lung
    0.06
    Resistance
    0.06
     الذي
    0.06
    enci
    0.06
     आश
    0.06
     alumni
    0.06
    이크
    0.06
    .sendMessage
    0.05
    �
    0.05
    Act Density 0.038%

    No Known Activations