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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and quotation marks

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

    quotation marks followed by words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Shad
    -0.46
    ViewInit
    -0.46
    ViewImports
    -0.45
     Wikimedijinoj
    -0.45
     MainAxisSize
    -0.45
     Ender
    -0.44
    UserScript
    -0.42
     désolés
    -0.42
    udert
    -0.41
    ListItemIcon
    -0.41
    POSITIVE LOGITS
     doInBackground
    0.45
     Gauthier
    0.44
     Maldonado
    0.43
    SuppressLint
    0.43
     Darauf
    0.42
     Keluarga
    0.42
     morphine
    0.41
    icleta
    0.41
     Sweeney
    0.41
    Garcia
    0.41
    Act Density 0.048%

    No Known Activations