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

    Neuronpedia

    INDEX
    Explanations

    small text files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IER
    0.48
    ција
    0.47
    NING
    0.46
    ول
    0.45
    oxine
    0.44
    вки
    0.44
    ود
    0.43
    واس
    0.43
    ّ
    0.43
     inversa
    0.43
    POSITIVE LOGITS
    🏈
    0.50
     AppMethodBeat
    0.47
    🫡
    0.47
    getNumber
    0.46
    gameField
    0.46
     බොහෝ
    0.45
    🥞
    0.45
    🏕
    0.45
    🏉
    0.45
    .';
    0.45
    Act Density 0.002%

    No Known Activations