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

    Neuronpedia

    INDEX
    Explanations

    animation layers or parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ชุม
    0.45
    楖
    0.44
     کھ
    0.43
    Trading
    0.43
    前者
    0.43
    ించిన
    0.42
    береж
    0.42
     typology
    0.41
    Tourism
    0.41
    ဍ
    0.40
    POSITIVE LOGITS
     m
    0.67
    ParameterActive
    0.58
     parameter
    0.52
     dance
    0.50
     Parameter
    0.47
    m
    0.46
    Parameter
    0.46
     ballet
    0.46
     paramet
    0.45
     animator
    0.45
    Act Density 0.001%

    No Known Activations