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

    Neuronpedia

    INDEX
    Explanations

    shy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trad
    -0.07
    saldo
    -0.06
    اختی
    -0.06
     Val
    -0.06
    Rendering
    -0.06
     Observ
    -0.06
    alte
    -0.06
    dfd
    -0.06
    reste
    -0.06
    Flex
    -0.06
    POSITIVE LOGITS
     shy
    0.14
     sly
    0.08
     ^{}
    0.08
    SelfPermission
    0.07
    y
    0.07
     bravery
    0.07
     Sly
    0.06
    >(()
    0.06
    enth
    0.06
     Streams
    0.06
    Act Density 0.004%

    No Known Activations