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

    Neuronpedia

    INDEX
    Explanations

    languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    장을
    -0.07
     //@
    -0.06
     tác
    -0.06
     ситуации
    -0.06
    udem
    -0.06
     ot
    -0.06
    illow
    -0.06
    igans
    -0.06
    eight
    -0.06
    amam
    -0.06
    POSITIVE LOGITS
    ApiResponse
    0.07
    ﾆﾆﾆﾆ
    0.07
     العامة
    0.06
     binary
    0.06
     Relevant
    0.06
     espect
    0.06
     disturbed
    0.06
    _In
    0.06
    ايت
    0.06
    (INVOKE
    0.06
    Act Density 0.013%

    No Known Activations