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

    Neuronpedia

    INDEX
    Explanations

    programming language syntax and import statements

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

    Code import statements

    np_acts-logits-general · gemini-2.0-flash

    imports and packages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OMITBAD
    -0.81
     itſelf
    -0.80
     Cæsar
    -0.78
     المعيارى
    -0.77
     فريبيس
    -0.74
     QWidget
    -0.72
     asiatique
    -0.72
     WebDriverWait
    -0.71
     dentaire
    -0.71
     estekak
    -0.71
    POSITIVE LOGITS
    ing
    0.57
    ↵↵↵↵
    0.52
     importante
    0.49
    ↵↵
    0.48
     مهم
    0.48
    ssa
    0.47
    ienti
    0.46
     I
    0.45
    ])).
    0.45
    ↵↵↵↵↵↵
    0.45
    Act Density 0.138%

    No Known Activations