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

    Neuronpedia

    INDEX
    Explanations

    sexually suggestive content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     at
    0.77
     to
    0.68
     as
    0.52
     on
    0.52
     an
    0.52
     from
    0.51
    NetAmount
    0.50
    ので
    0.50
     بجائے
    0.50
     that
    0.49
    POSITIVE LOGITS
    -
    0.70
    í
    0.56
    az
    0.52
    us
    0.52
    ي
    0.51
    <0xB2>
    0.51
    i
    0.51
    0.50
    (
    0.49
    ти
    0.49
    Act Density 0.226%

    No Known Activations