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

    Neuronpedia

    INDEX
    Explanations

    elements related to message handling and protocol definitions in programming contexts

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

    Code containing parentheses and numbers

    np_acts-logits-general · gemini-2.0-flash

    function calls or initializations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.93
    __':
    -0.89
    __":
    -0.86
     myſelf
    -0.85
     raiſ
    -0.84
     Majefty
    -0.82
    تقاوى
    -0.81
     ſever
    -0.81
     ſeveral
    -0.80
    EndGlobalSection
    -0.79
    POSITIVE LOGITS
    ()
    0.58
    (),
    0.51
    ();
    0.50
     di
    0.49
     ()
    0.47
    (
    0.45
    ().
    0.44
    ())
    0.42
     form
    0.42
     Cole
    0.41
    Act Density 0.227%

    No Known Activations