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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and control flow keywords in code

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

    Code that includes logical negation

    np_acts-logits-general · gemini-2.0-flash

    if followed by parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.75
    esez
    -0.67
     للمعارف
    -0.66
     Wikimedijinoj
    -0.63
     تانيه
    -0.62
     HasFactory
    -0.62
    rungsseite
    -0.60
    كويكب
    -0.60
     برانيه
    -0.60
    WithIOException
    -0.59
    POSITIVE LOGITS
     !
    1.00
     !$
    0.90
    (!
    0.89
     (!
    0.84
    {!
    0.82
     not
    0.80
    (!$
    0.77
     (!$
    0.74
    not
    0.73
    :!
    0.70
    Act Density 0.084%

    No Known Activations