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

    Neuronpedia

    INDEX
    Explanations

    urinary excretion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     are
    0.35
    '
    0.33
    Water
    0.29
    "
    0.29
    Window
    0.28
    H
    0.28
    lemon
    0.27
    W
    0.27
    Mess
    0.27
    juice
    0.27
    POSITIVE LOGITS
    ש
    0.40
    ้
    0.35
     коэффициент
    0.34
     rougeâtre
    0.33
    ী
    0.33
     idempotent
    0.32
     leichte
    0.32
    ח
    0.32
     собственные
    0.31
    ை
    0.31
    Act Density 0.000%

    No Known Activations