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

    Neuronpedia

    INDEX
    Explanations

    not/no

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sağ
    -0.07
    _MIN
    -0.07
    527
    -0.06
    �述
    -0.06
    ASET
    -0.06
    ८
    -0.06
    auses
    -0.06
    Sprites
    -0.06
    .sorted
    -0.06
    <Tag
    -0.06
    POSITIVE LOGITS
     suppressing
    0.07
    .norm
    0.07
    ým
    0.06
    Pers
    0.06
     Auckland
    0.06
     reinforces
    0.06
    Care
    0.06
     universally
    0.06
     didnt
    0.06
    باز
    0.06
    Act Density 0.053%

    No Known Activations