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

    Neuronpedia

    INDEX
    Explanations

    code snippets containing punctuation and special characters

    oai_token-act-pair · gemini-2.0-flash

    parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disponibilités
    -0.68
    QMetaType
    -0.60
     سكانية
    -0.58
     الدولى
    -0.56
     оригіналу
    -0.56
    setVerticalGroup
    -0.56
     getSource
    -0.56
    -0.56
     Chwiliwch
    -0.55
    FOOTNOTES
    -0.55
    POSITIVE LOGITS
     Majefty
    0.60
     pleaſure
    0.50
    <bos>
    0.50
     occaf
    0.49
     tayo
    0.49
     Socrates
    0.49
     poffible
    0.49
    argout
    0.49
    EndContext
    0.48
    ulás
    0.48
    Act Density 2.915%

    No Known Activations