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

    Neuronpedia

    INDEX
    Explanations

    references to essays and articles

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

    essays, articles, or posts

    np_acts-logits-general · gemini-2.0-flash

    essay or article title

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.59
    ]='\
    -0.56
    .*")]
    -0.56
    SerializeField
    -0.55
     TAMBÉM
    -0.53
    represented
    -0.50
    anstalt
    -0.49
    fficients
    -0.48
    localtime
    -0.48
    CGContext
    -0.47
    POSITIVE LOGITS
     entitled
    0.73
     explaining
    0.63
     titled
    0.60
     detailing
    0.59
     dated
    0.57
     concerning
    0.57
    beitrag
    0.57
     discussing
    0.57
    GTCX
    0.56
     penned
    0.55
    Act Density 0.610%

    No Known Activations