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

    Neuronpedia

    INDEX
    Explanations

    non-English languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Uid
    -0.07
     Axios
    -0.07
    Beautiful
    -0.06
     Speak
    -0.06
     полов
    -0.06
    _selector
    -0.06
     Yaş
    -0.06
     youre
    -0.06
     blij
    -0.06
     Их
    -0.06
    POSITIVE LOGITS
     augmented
    0.07
     TE
    0.07
    cidade
    0.07
     احتم
    0.07
     sever
    0.06
    bate
    0.06
    σ
    0.06
    لو
    0.06
    ьи
    0.06
    NASDAQ
    0.06
    Act Density 0.108%

    No Known Activations