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

    Neuronpedia

    INDEX
    Explanations

    documentation, websites, CI/CD pipelines,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    consent
    0.54
     Consent
    0.52
     consent
    0.49
     훨씬
    0.48
     বিশুদ্ধ
    0.46
     issu
    0.46
    ငန်း
    0.46
     factorizar
    0.45
    olev
    0.45
     Strept
    0.45
    POSITIVE LOGITS
    OS
    0.49
    Year
    0.48
    NSMakeRange
    0.48
    CAR
    0.47
    Inicio
    0.47
    िओ
    0.47
    Greet
    0.45
    Ok
    0.45
    DOM
    0.45
    Youth
    0.45
    Act Density 0.009%

    No Known Activations