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

    Neuronpedia

    INDEX
    Explanations

    specifying type or general types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CubeSize
    0.42
    OutSize
    0.40
    Kelly
    0.39
     সময়ে
    0.39
     raping
    0.38
    Russell
    0.37
    Uuid
    0.37
    melt
    0.37
     raped
    0.36
    Hall
    0.36
    POSITIVE LOGITS
     ordinary
    0.80
     일반
    0.78
    普通
    0.75
     type
    0.74
     普通
    0.73
    普通的
    0.72
     tipo
    0.66
     обы
    0.66
     обычной
    0.66
    ordinary
    0.64
    Act Density 0.056%

    No Known Activations