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

    Neuronpedia

    INDEX
    Explanations

    scientific and technical contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ѷ
    -0.08
    嫽
    -0.07
    (gulp
    -0.07
    ✩
    -0.07
    ביטוח
    -0.07
    湑
    -0.07
    uğu
    -0.07
    㐂
    -0.07
    ﮫ
    -0.07
    ünk
    -0.07
    POSITIVE LOGITS
     aph
    0.08
     resid
    0.08
     aplic
    0.07
     visualization
    0.07
    _deriv
    0.07
    様
    0.07
    的眼
    0.07
     Wol
    0.06
    hil
    0.06
    _transform
    0.06
    Act Density 0.143%

    No Known Activations