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

    Neuronpedia

    INDEX
    Explanations

    ASMR roleplay script artist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    1.98
    е
    1.41
    При
    1.12
    O
    1.11
    إن
    1.10
    لما
    1.10
    د
    1.05
    Пер
    1.02
    обходи
    1.02
    푸
    1.02
    POSITIVE LOGITS
    s
    1.45
    ing
    1.27
    ט
    1.18
    ta
    1.11
    ING
    1.08
    f
    1.08
     are
    1.05
    6
    0.99
    4
    0.98
    the
    0.98
    Act Density 0.000%

    No Known Activations