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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a lack of knowledge or understanding about a subject

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

    not known

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.64
    vorschaubild
    -0.58
    sqcup
    -0.58
     هی
    -0.56
    beging
    -0.56
    izzle
    -0.56
    depth
    -0.55
    pulseira
    -0.55
     Cuc
    -0.55
    ctile
    -0.55
    POSITIVE LOGITS
     known
    1.14
     Known
    1.12
    Known
    1.05
    known
    1.01
     KNOWN
    0.98
    KNOWN
    0.96
    Know
    0.91
     Know
    0.88
     know
    0.83
     Knows
    0.77
    Act Density 0.023%

    No Known Activations