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

    Neuronpedia

    INDEX
    Explanations

    contextual links and sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    se
    0.82
    t
    0.80
    o
    0.69
     we
    0.68
    á
    0.68
    e
    0.62
    et
    0.61
     hekt
    0.61
    ουμε
    0.61
    in
    0.60
    POSITIVE LOGITS
    的服务
    0.64
    ’
    0.62
     والم
    0.61
     של
    0.60
     באופן
    0.60
     كتاب
    0.60
    ման
    0.60
    та
    0.59
    の内容
    0.58
    :
    0.57
    Act Density 0.000%

    No Known Activations