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

    Neuronpedia

    INDEX
    Explanations

    parentheses and their usage in expressions

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

    Closing parenthesis/brackets in code

    np_acts-logits-general · gemini-2.0-flash

    closing punctuation, then operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     critical
    -0.64
    anja
    -0.61
    alai
    -0.60
    toft
    -0.57
     Del
    -0.57
    ity
    -0.56
    hø
    -0.56
    osh
    -0.55
     Kle
    -0.55
    omy
    -0.55
    POSITIVE LOGITS
    +#+#
    1.12
    }{*}{}
    0.95
     Picchu
    0.92
    complexContent
    0.85
     Kenobi
    0.82
     تانيه
    0.82
     propOrder
    0.81
    ]")]
    0.80
     referenties
    0.79
    Vidite
    0.79
    Act Density 0.182%

    No Known Activations