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

    Neuronpedia

    INDEX
    Explanations

    changes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ि,
    -0.07
    τη
    -0.06
     neces
    -0.06
    ่าเป
    -0.06
    [maxn
    -0.06
    (todo
    -0.06
     mít
    -0.06
     demokrat
    -0.06
    ống
    -0.06
     unlucky
    -0.06
    POSITIVE LOGITS
     треб
    0.07
     Seed
    0.07
    croft
    0.07
     Jensen
    0.06
    Ο
    0.06
    вок
    0.06
    etal
    0.06
     Ariel
    0.06
     سوم
    0.06
     Гол
    0.06
    Act Density 0.051%

    No Known Activations