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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     schl
    -0.06
    (SQL
    -0.06
     rd
    -0.06
    들
    -0.06
    ’m
    -0.06
    _UNDEF
    -0.06
     Owens
    -0.06
     equal
    -0.06
     yık
    -0.06
     impressive
    -0.06
    POSITIVE LOGITS
    colon
    0.08
     матері
    0.07
    стра
    0.07
    ा:
    0.07
     тобі
    0.07
    muştur
    0.07
    Brun
    0.07
    dıkları
    0.07
    igmat
    0.07
     pcm
    0.06
    Act Density 0.010%

    No Known Activations