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

    Neuronpedia

    INDEX
    Explanations

    punctuation and special characters in a programming context

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

    Code snippets with commas or brackets

    np_acts-logits-general · gemini-2.0-flash

    list delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.77
    windowFixed
    -0.73
    RenderAtEndOf
    -0.71
    SequentialGroup
    -0.64
    kloped
    -0.60
    balleur
    -0.59
     Signalez
    -0.59
     Efq
    -0.59
    UrlResolution
    -0.58
     cherchés
    -0.58
    POSITIVE LOGITS
    ↵
    0.67
     **
    0.60
    **
    0.60
     dry
    0.57
    مصادر
    0.55
     name
    0.53
     method
    0.52
    True
    0.51
    ughter
    0.51
     capacity
    0.50
    Act Density 0.208%

    No Known Activations