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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rubbing
    -0.07
     ráp
    -0.07
    TRAN
    -0.07
     необходим
    -0.06
    rying
    -0.06
     long
    -0.06
     integrated
    -0.06
    PURE
    -0.06
    _air
    -0.06
     стратег
    -0.06
    POSITIVE LOGITS
     〈
    0.06
    ucas
    0.06
    RCT
    0.06
    (scroll
    0.06
    øj
    0.06
    omal
    0.06
     politicians
    0.06
    saldo
    0.06
    _cached
    0.06
     Daw
    0.06
    Act Density 0.073%

    No Known Activations