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

    Neuronpedia

    INDEX
    Explanations

    commitments and markets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ד
    1.22
    局面
    1.19
    ͯ
    1.16
    특별시
    1.15
     Scrooge
    1.12
     earners
    1.09
     Fellow
    1.09
     Uhuru
    1.09
    و
    1.06
    ர்
    1.05
    POSITIVE LOGITS
    ors
    1.41
    o
    1.36
    ion
    1.17
    ev
    1.16
    ed
    1.10
    aneous
    1.08
    قية
    1.05
    ोष
    1.03
    ar
    1.02
    rawal
    1.02
    Act Density 0.000%

    No Known Activations