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

    Neuronpedia

    INDEX
    Explanations

    hatch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    彩èī²
    -0.29
     ",č↵
    -0.27
     :";↵
    -0.25
     "),↵
    -0.25
    PerPixel
    -0.25
     TER
    -0.25
    :",↵
    -0.25
    :',↵
    -0.23
    å±Ĭæ¯ķä¸ļçĶŁ
    -0.23
    arges
    -0.23
    POSITIVE LOGITS
    relude
    0.28
    æ¿ī
    0.27
    ognito
    0.26
    é¦ĸ
    0.25
    uele
    0.24
    课
    0.24
    èİŀ
    0.24
    éĤĽ
    0.23
    SB
    0.23
    âİ
    0.23
    Act Density 0.004%

    No Known Activations