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

    Neuronpedia

    INDEX
    Explanations

    areas and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    0.88
    р
    0.86
    ट
    0.84
    м
    0.79
    たと
    0.73
    r
    0.72
    ق
    0.68
    naire
    0.67
    m
    0.67
    Type
    0.67
    POSITIVE LOGITS
    领域
    1.23
     медици
    1.13
     ciencias
    1.12
     ciências
    1.11
     assuntos
    1.10
     temática
    1.09
    sciences
    1.08
     scienze
    1.07
    领域的
    1.05
     lĩnh
    1.03
    Act Density 0.932%

    No Known Activations