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

    Neuronpedia

    INDEX
    Explanations

    wireframes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ية
    1.16
    ﺮ
    0.82
    ский
    0.75
    larını
    0.74
    ра
    0.73
    '
    0.71
    DepartTime
    0.70
    \
    0.70
    ды
    0.68
    ième
    0.68
    POSITIVE LOGITS
    K
    0.94
    T
    0.92
    ↵
    0.89
     knit
    0.84
    O
    0.84
     we
    0.82
    N
    0.79
    ों
    0.78
     heterosexual
    0.77
     idiom
    0.76
    Act Density 0.001%

    No Known Activations