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

    Neuronpedia

    INDEX
    Explanations

    Technical descriptions/reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yerde
    -0.07
     witty
    -0.07
    .%
    -0.07
    -0.06
    bout
    -0.06
     prevailing
    -0.06
     tonnes
    -0.06
    ्ज
    -0.06
     ration
    -0.06
     selbst
    -0.06
    POSITIVE LOGITS
    Ana
    0.07
     Gr
    0.07
     věd
    0.06
    UID
    0.06
    紫
    0.06
    -W
    0.06
    _prefs
    0.06
    irthday
    0.06
     çıkış
    0.06
     Daisy
    0.05
    Act Density 0.106%

    No Known Activations