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

    Neuronpedia

    INDEX
    Explanations

    technical terms and conditions related to programming and algorithms

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

    error rate, probability calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.47
     }{@
    -0.44
     SwitchCompat
    -0.41
    JspWriter
    -0.39
     iprot
    -0.39
    ManagedBean
    -0.38
     nltk
    -0.35
     للاسماء
    -0.35
    OGND
    -0.35
     الإنترنت
    -0.35
    POSITIVE LOGITS
    原始内容存档于
    0.47
     serius
    0.45
     defaultstate
    0.41
     barriga
    0.41
    ascin
    0.41
     détaillée
    0.39
    Билгалдахарш
    0.38
     Nationwide
    0.38
    Servus
    0.38
     barriers
    0.38
    Act Density 0.240%

    No Known Activations