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

    Neuronpedia

    INDEX
    Explanations

    pleasuring herself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.38
    in
    1.16
    inę
    1.14
     you
    1.13
    der
    1.10
    houses
    1.09
    you
    1.05
    tin
    1.05
    いた
    1.04
    I
    1.02
    POSITIVE LOGITS
    。
    1.25
    '
    1.09
    ќ
    1.06
    ’
    1.02
    來
    0.99
    0.96
    ー
    0.96
    and
    0.95
    ة
    0.92
    的
    0.92
    Act Density 0.000%

    No Known Activations