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

    Neuronpedia

    INDEX
    Explanations

    modal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kü
    -0.08
    ucked
    -0.07
     personn
    -0.07
     canv
    -0.07
    _disk
    -0.07
    Upper
    -0.07
     paran
    -0.06
    (layers
    -0.06
    infinity
    -0.06
     vile
    -0.06
    POSITIVE LOGITS
     lemma
    0.08
     Company
    0.07
    .Options
    0.07
     avis
    0.07
     bonus
    0.07
     Margin
    0.07
     注意
    0.07
     Grant
    0.07
    .Camera
    0.07
    .movie
    0.07
    Act Density 0.005%

    No Known Activations