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

    Neuronpedia

    INDEX
    Explanations

    occurrences of indentation or whitespace patterns in code

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

    programming keywords and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cyfarwyddwr
    -0.39
    Hauptartikel
    -0.39
     ?>/
    -0.39
    SBATCH
    -0.38
    yym
    -0.38
     BoxFit
    -0.38
    argout
    -0.38
    TypeOf
    -0.37
    UREAU
    -0.37
    gatsby
    -0.37
    POSITIVE LOGITS
    DoubleQuotes
    0.53
     vuestros
    0.51
    󠁢
    0.46
     iconLine
    0.41
     /*#__
    0.40
    çoivent
    0.39
    UnusedPrivate
    0.38
     pourraient
    0.38
     nôtre
    0.37
     descubre
    0.37
    Act Density 0.175%

    No Known Activations