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

    Neuronpedia

    INDEX
    Explanations

    основ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    בשר
    -0.07
    	org
    -0.06
    工委
    -0.06
    腧
    -0.06
     phát
    -0.06
    QUIRED
    -0.06
    İZ
    -0.06
    نفذ
    -0.06
    טקס
    -0.06
    (dynamic
    -0.06
    POSITIVE LOGITS
    's
    0.08
    正确的
    0.07
    屿
    0.07
    它们
    0.07
    Url
    0.07
    us
    0.07
    县城
    0.07
     nave
    0.07
     hsv
    0.07
     hull
    0.06
    Act Density 0.014%

    No Known Activations