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

    Neuronpedia

    INDEX
    Explanations

    To Kill a Mockingbird

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    h
    0.68
     спортс
    0.63
    y
    0.62
    u
    0.60
    i
    0.58
    6
    0.58
     леса
    0.57
    4
    0.55
    спорт
    0.54
     nhàng
    0.54
    POSITIVE LOGITS
    োপাধ
    0.59
     LEG
    0.57
     rake
    0.54
     ਕਿ
    0.54
    )،
    0.52
     appunto
    0.51
     LRC
    0.51
    itoti
    0.49
     CCA
    0.49
    كت
    0.49
    Act Density 0.013%

    No Known Activations