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

    Neuronpedia

    INDEX
    Explanations

    references to official documents or sources

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

    information from urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.56
     Réponses
    -0.47
     ब्रेकडाउन
    -0.44
     autorytatywna
    -0.42
    HideFlags
    -0.41
    parsedMessage
    -0.40
     vertelt
    -0.39
    Ӕ
    -0.39
    awtextra
    -0.38
     prowadzi
    -0.38
    POSITIVE LOGITS
     AssemblyTitle
    0.54
    twimg
    0.50
    ftagPool
    0.48
     appunto
    0.48
     Geo
    0.48
    ModelForm
    0.47
    }}^
    0.44
     Urqu
    0.43
     Dodson
    0.43
     _
    0.42
    Act Density 0.041%

    No Known Activations