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

    Neuronpedia

    INDEX
    Explanations

    ice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    æłijæŀĹ
    -0.31
    ầu
    -0.28
     Purs
    -0.26
     exposure
    -0.26
     isOpen
    -0.25
    害ç¾ŀ
    -0.25
    _Map
    -0.25
     todd
    -0.24
     tù
    -0.24
     halfway
    -0.24
    POSITIVE LOGITS
    æľīèī²
    0.25
    çļĦçIJĨçĶ±
    0.25
    bere
    0.25
    åı¦ä¸Ģä½į
    0.24
    клÑİÑĩа
    0.24
    romo
    0.24
    æĪIJç«ĭ以æĿ¥
    0.24
    æŁ°
    0.24
    olest
    0.24
    пиÑģÑĭва
    0.24
    Act Density 0.002%

    No Known Activations