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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols in the text

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

    References or citations (often bracketed)

    np_acts-logits-general · gemini-2.0-flash

    academic labels or citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     indisponible
    -0.57
    WithMany
    -0.51
     @"/
    -0.51
    rativa
    -0.49
    بوابة
    -0.48
    bedo
    -0.47
    ourge
    -0.47
    onViewCreated
    -0.45
    íše
    -0.45
     désolés
    -0.44
    POSITIVE LOGITS
     cohomology
    0.70
    脚注の使い方
    0.66
     Homicide
    0.61
    tvguidetime
    0.60
     Herod
    0.59
    reibung
    0.59
     snout
    0.58
    AddWithValue
    0.58
     Laplacian
    0.58
     blasphemy
    0.57
    Act Density 0.299%

    No Known Activations