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

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives indicating high quality or aesthetics

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

    descriptive positive adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.52
     HttpNotFound
    -0.52
     dAtA
    -0.47
    內容簡介
    -0.44
     Préférences
    -0.44
     CURLOPT
    -0.44
     ApiException
    -0.42
    turnstile
    -0.41
    esía
    -0.41
    ± 
    -0.41
    POSITIVE LOGITS
    lectic
    0.47
    ToBounds
    0.47
    Accurate
    0.45
     enough
    0.42
     Accurate
    0.41
    localctx
    0.40
    IsMutable
    0.40
     japoneses
    0.39
    SuppressMessage
    0.39
    Amazing
    0.38
    Act Density 0.030%

    No Known Activations