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

    Neuronpedia

    INDEX
    Explanations

    actions and achievements that indicate dominance or superiority in performance

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

    Signals positive sentiment

    np_acts-logits-general · gemini-2.0-flash

    power and excellence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SpringRunner
    -0.53
    MigrationBuilder
    -0.42
    AnchorTagHelper
    -0.41
    __*/
    -0.36
    SequentialGroup
    -0.36
    $​
    -0.36
    Péri
    -0.35
    Filmografia
    -0.35
    rrggbb
    -0.35
    Obrázky
    -0.35
    POSITIVE LOGITS
     awesome
    0.60
     outstanding
    0.58
     brilliance
    0.57
    Awesome
    0.57
     Outstanding
    0.57
     greatness
    0.57
     excels
    0.57
     geweldige
    0.56
     Awesome
    0.56
     AWESOME
    0.56
    Act Density 0.339%

    No Known Activations