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

    Neuronpedia

    INDEX
    Explanations

    includes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mür
    -0.07
    apus
    -0.06
    なく
    -0.06
     conex
    -0.06
     Emit
    -0.06
    MV
    -0.06
    nk
    -0.06
    τηση
    -0.06
    ence
    -0.06
    єш
    -0.06
    POSITIVE LOGITS
     Profile
    0.07
     endorsements
    0.07
     관계
    0.06
     Bloom
    0.06
    .persistence
    0.06
     холодиль
    0.06
     OPER
    0.06
     processes
    0.06
     warranty
    0.06
    DEPEND
    0.06
    Act Density 0.000%

    No Known Activations