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

    Neuronpedia

    INDEX
    Explanations

    As a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.70
    '
    0.70
    /
    0.67
    :
    0.66
    ",
    0.65
    ".
    0.64
    ',
    0.62
    ().
    0.61
    \
    0.60
    .
    0.59
    POSITIVE LOGITS
    ymptotic
    0.70
    uparavant
    0.63
     قلنا
    0.61
    sembling
    0.61
    cribable
    0.58
    ymmet
    0.57
    sembled
    0.57
    sembles
    0.56
    cribing
    0.56
    inine
    0.56
    Act Density 0.008%

    No Known Activations