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

    Neuronpedia

    INDEX
    Explanations

    expansion or codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    percent
    0.45
    enh
    0.44
    quick
    0.43
    defini
    0.43
    )."
    0.42
    óln
    0.41
    ától
    0.41
    enee
    0.41
    ewnątrz
    0.40
    ším
    0.40
    POSITIVE LOGITS
    もう
    0.47
    సా
    0.45
    ワ
    0.45
     haemat
    0.44
     Вам
    0.43
    蕁
    0.43
     الع
    0.43
     Trevor
    0.43
    お子
    0.42
    ファ
    0.42
    Act Density 0.000%

    No Known Activations