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

    Neuronpedia

    INDEX
    Explanations

    logical constructs and expressions in programming contexts

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

    Code or data snippets containing special characters

    np_acts-logits-general · gemini-2.0-flash

    logical comparison expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ***!
    -0.65
     ""))
    -0.65
    Попис
    -0.63
    intios
    -0.62
    $")
    -0.59
    providedIn
    -0.58
    "])
    -0.58
    ronpa
    -0.57
    findpost
    -0.57
     '.';
    -0.57
    POSITIVE LOGITS
     comparison
    0.97
     condition
    0.91
     comparisons
    0.89
    Condition
    0.88
     Comparison
    0.87
     Condition
    0.86
     Comparisons
    0.85
    comparison
    0.82
    Comparison
    0.82
     expression
    0.82
    Act Density 0.553%

    No Known Activations