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

    Neuronpedia

    INDEX
    Explanations

    negative aspects or criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Numbers connected by hyphens

    np_acts-logits-general · gemini-2.0-flash

    numbers and hyphens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    -1.51
    (
    -1.21
    "
    -0.96
    \
    -0.85
    $
    -0.84
    .
    -0.83
    ,
    -0.79
    /
    -0.77
    _
    -0.70
    [
    -0.70
    POSITIVE LOGITS
    &-
    0.96
    based
    0.84
    related
    0.79
    {}'.
    0.76
    =-=-=-=-
    0.76
     }}-
    0.76
    shaped
    0.75
    =-=-
    0.74
    *-*-
    0.73
    themed
    0.73
    Act Density 1.302%

    No Known Activations