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

    Neuronpedia

    INDEX
    Explanations

    AS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     язы
    -0.07
    凉
    -0.06
     만들
    -0.06
    apk
    -0.06
     gelişim
    -0.06
    aded
    -0.06
    virt
    -0.06
    come
    -0.06
    -либо
    -0.06
     Nath
    -0.06
    POSITIVE LOGITS
    _BITMAP
    0.07
    resizing
    0.06
    otts
    0.06
    .white
    0.06
    )(*
    0.06
     Fighting
    0.06
     undertaking
    0.06
     restore
    0.06
     heterosexual
    0.06
     Times
    0.06
    Act Density 0.001%

    No Known Activations