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

    Neuronpedia

    INDEX
    Explanations

    Coordinated Universal Time (UTC)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    1.73
    িন
    1.47
    enças
    1.40
    aneously
    1.38
    रम
    1.37
    ANEOUS
    1.37
    S
    1.33
    ्य
    1.32
    ians
    1.30
     súa
    1.29
    POSITIVE LOGITS
     پیسو
    1.76
    čaj
    1.64
     exalted
    1.63
     Kohl
    1.63
    كب
    1.57
    𝜋
    1.49
     axiomatic
    1.46
     долларов
    1.45
    weisung
    1.43
    ያዎች
    1.42
    Act Density 0.000%

    No Known Activations