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

    Neuronpedia

    INDEX
    Explanations

    ceramide, eviscerated, incarcerated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    觏
    -3.13
    ൎ
    -3.09
    -3.05
    鋱
    -3.05
     奶茶
    -3.00
    而去
    -2.98
    雠
    -2.92
    驺
    -2.88
    -2.88
    㐂
    -2.84
    POSITIVE LOGITS
    u
    2.98
    i
    2.91
    or
    2.88
    3
    2.88
    5
    2.77
    8
    2.75
    7
    2.63
    er
    2.50
    ing
    2.45
    ed
    2.42
    Act Density 0.009%

    No Known Activations