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

    Neuronpedia

    INDEX
    Explanations

    mish

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .SC
    -0.06
     Saudi
    -0.06
    Percent
    -0.06
     Christmas
    -0.06
     Potential
    -0.06
    Initializer
    -0.06
    /order
    -0.06
    َس
    -0.06
     structs
    -0.06
    odiac
    -0.06
    POSITIVE LOGITS
     mish
    0.07
    RESH
    0.07
    えた
    0.07
    紀
    0.06
     prova
    0.06
     हम
    0.06
    인가
    0.06
    ndef
    0.06
    'h
    0.06
     sơn
    0.06
    Act Density 0.001%

    No Known Activations