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

    Neuronpedia

    INDEX
    Explanations

    LEGO sets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    初始化
    -0.07
    :absolute
    -0.07
    裝
    -0.06
     calcul
    -0.06
    _draw
    -0.06
    .frame
    -0.06
     FIT
    -0.06
     caus
    -0.06
    าษ
    -0.06
     stitch
    -0.06
    POSITIVE LOGITS
    _TODO
    0.07
     slaughtered
    0.07
     wiping
    0.06
     Ethan
    0.06
     *__
    0.06
     Pvt
    0.06
    205
    0.06
     ایشان
    0.06
    .genre
    0.06
    tal
    0.06
    Act Density 0.006%

    No Known Activations