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

    Neuronpedia

    INDEX
    Explanations

    document and code templates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    は
    1.48
    는
    1.36
    จะ
    1.31
    อย่าง
    1.25
    .
    1.20
    p
    1.18
    ments
    1.17
    子の
    1.16
    ing
    1.16
    ă
    1.14
    POSITIVE LOGITS
    ER
    1.31
    توان
    1.23
    ０
    1.23
    ل
    1.19
    ر
    1.10
     einfacher
    1.09
    Ts
    1.09
    UT
    1.08
    лла
    1.08
    $.
    1.06
    Act Density 0.039%

    No Known Activations