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

    Neuronpedia

    INDEX
    Explanations

    similar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     preceded
    -0.08
    ber
    -0.07
    РА
    -0.07
    _To
    -0.07
    塔
    -0.06
     updating
    -0.06
    BERS
    -0.06
     aspiring
    -0.06
     تكييف
    -0.06
    香
    -0.06
    POSITIVE LOGITS
     Vuex
    0.06
    ових
    0.06
    不是
    0.06
    이었
    0.06
    .Linq
    0.06
    (rx
    0.06
    restrict
    0.06
     nied
    0.06
     rè
    0.06
     자세
    0.06
    Act Density 0.007%

    No Known Activations