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

    Neuronpedia

    INDEX
    Explanations

    viewport meta tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    га
    1.79
    จะ
    1.44
    ﺤ
    1.41
    ний
    1.40
     hives
    1.28
    ເພ
    1.26
     đu
    1.25
    n
    1.23
    ﻜ
    1.22
    מד
    1.21
    POSITIVE LOGITS
    ૦
    1.35
    ATION
    1.31
     êtres
    1.29
    ς
    1.28
    رة
    1.27
     édition
    1.27
    yards
    1.25
     considérons
    1.25
    ין
    1.23
     évaluation
    1.23
    Act Density 0.002%

    No Known Activations