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

    Neuronpedia

    INDEX
    Explanations

    function calls and syntax elements in code

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

    parentheses and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.62
    aarrggbb
    -0.59
     AssemblyCulture
    -0.58
     Chwiliwch
    -0.58
    UserScript
    -0.55
    MemoryWarning
    -0.53
     doInBackground
    -0.53
     ComVisible
    -0.53
    AndEndTag
    -0.53
    transQ
    -0.52
    POSITIVE LOGITS
     közül
    0.43
     totaling
    0.40
     including
    0.38
     conjunta
    0.37
     neler
    0.37
     jotka
    0.36
     []*
    0.36
     parties
    0.36
     recueil
    0.35
     semanal
    0.34
    Act Density 0.008%

    No Known Activations