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

    Neuronpedia

    INDEX
    Explanations

    specific formatting elements and coding syntax in text

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

    technical terms with hyphens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Grüsse
    -0.59
     bordada
    -0.56
     auroit
    -0.54
     gethan
    -0.54
     feroit
    -0.53
     desmotivaciones
    -0.52
     pouvoit
    -0.51
     Gerechtigkeit
    -0.51
    antaranya
    -0.50
    geschlossen
    -0.49
    POSITIVE LOGITS
    -
    1.41
    '-
    0.97
    ‐
    0.95
    -\
    0.91
     -
    0.91
    *-
    0.90
    }-
    0.86
    $-
    0.86
    »-
    0.86
    ®-
    0.84
    Act Density 0.185%

    No Known Activations