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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zdroj
    -0.07
    층의
    -0.07
     větší
    -0.07
    들의
    -0.07
     naam
    -0.07
     Fate
    -0.07
    개의
    -0.07
    )는
    -0.06
     Dud
    -0.06
     заг
    -0.06
    POSITIVE LOGITS
    499
    0.07
     Carlson
    0.06
    _MPI
    0.06
    (pr
    0.06
    (tv
    0.06
     (?
    0.06
    시오
    0.06
    echan
    0.06
    彩
    0.06
     спеці
    0.06
    Act Density 0.000%

    No Known Activations