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

    Neuronpedia

    INDEX
    Explanations

    Testing, information, diagnosis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ро
    1.34
    伍章
    1.24
    ización
    1.18
    ृत
    1.16
     dito
    1.13
     enfermos
    1.12
    第壹百
    1.09
    Mongo
    1.09
    なんか
    1.08
     rougeâtres
    1.08
    POSITIVE LOGITS
    ll
    1.58
    bold
    1.23
    llll
    1.04
     forth
    1.03
     تعالی
    1.02
    nd
    0.97
    re
    0.96
    disciplinary
    0.96
    0.96
    لم
    0.95
    Act Density 0.000%

    No Known Activations