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

    Neuronpedia

    INDEX
    Explanations

    stopwords

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    achs
    -0.07
    /grpc
    -0.07
     illumin
    -0.07
     teas
    -0.07
    _embedding
    -0.06
    槭
    -0.06
    万元
    -0.06
     Truck
    -0.06
     trước
    -0.06
     indebted
    -0.06
    POSITIVE LOGITS
    oron
    0.07
    也无法
    0.07
    contr
    0.06
     forgot
    0.06
    хож
    0.06
     louder
    0.06
    𝙍
    0.06
    barcode
    0.06
     плохо
    0.06
    ��
    0.06
    Act Density 0.004%

    No Known Activations