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

    Neuronpedia

    INDEX
    Explanations

    Negative sentiments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .future
    -0.07
     cries
    -0.07
     dang
    -0.07
     Parish
    -0.06
     fatto
    -0.06
    _chunk
    -0.06
    幼稚
    -0.06
    医学院
    -0.06
    osemite
    -0.06
     Soc
    -0.06
    POSITIVE LOGITS
    LAY
    0.08
    setParameter
    0.07
    🍜
    0.07
    (jTextField
    0.07
    不来
    0.07
     hút
    0.07
     eğ
    0.07
    קבע
    0.06
    不像
    0.06
    덥
    0.06
    Act Density 0.084%

    No Known Activations