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

    Neuronpedia

    INDEX
    Explanations

    placenta and obituary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    0.77
    {\
    0.71
    LLO
    0.71
    ۔
    0.68
    【
    0.66
    OR
    0.65
    UL
    0.65
    {
    0.65
    \
    0.64
    Qt
    0.63
    POSITIVE LOGITS
    p
    0.96
    ко
    0.93
    де
    0.84
    um
    0.77
    х
    0.77
    يد
    0.77
    ки
    0.75
    n
    0.75
    ка
    0.71
    c
    0.70
    Act Density 0.001%

    No Known Activations