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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their usage in text

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

    user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     traseira
    -0.54
    tonode
    -0.49
    IntoConstraints
    -0.48
     asegurarse
    -0.48
    yntaxException
    -0.47
     âmes
    -0.46
     natten
    -0.46
     âgé
    -0.46
    tagext
    -0.45
    BlockingQueue
    -0.45
    POSITIVE LOGITS
    Example
    0.58
     Example
    0.57
    +#+
    0.56
    EXAMPLE
    0.52
    example
    0.52
     ESM
    0.52
     Eva
    0.50
     Boy
    0.50
     Eval
    0.50
     Eas
    0.49
    Act Density 0.000%

    No Known Activations