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

    Neuronpedia

    INDEX
    Explanations

    conditions and restrictions related to probationary sentences

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

    conditions and restrictions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    richTextPanel
    -0.35
     تانيه
    -0.34
     fascinating
    -0.31
     beyond
    -0.31
    KeyPressed
    -0.30
    这个问题
    -0.30
    kör
    -0.29
     competitive
    -0.28
     вар
    -0.28
     intriguing
    -0.28
    POSITIVE LOGITS
    PreInfinity
    0.69
     Numerade
    0.61
    PropertyChanging
    0.59
    tableFuture
    0.58
    AutoModerator
    0.56
    ViewImports
    0.54
    tagext
    0.53
     queſta
    0.53
    ynomial
    0.53
     للمعارف
    0.53
    Act Density 0.042%

    No Known Activations