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

    Neuronpedia

    INDEX
    Explanations

    confidence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पंड
    0.43
    ಕು
    0.39
    cms
    0.39
    ̡
    0.38
    䔉
    0.37
    凉
    0.35
    رځ
    0.35
    CMS
    0.35
    cmap
    0.33
    ObjectMapper
    0.33
    POSITIVE LOGITS
     confidence
    3.27
     Confidence
    3.02
    Confidence
    3.02
    confidence
    2.92
    自信
    2.67
     confident
    2.55
     confianza
    2.45
     уверен
    2.45
     आत्मविश्वास
    2.45
     confiança
    2.39
    Act Density 0.037%

    No Known Activations