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

    Neuronpedia

    INDEX
    Explanations

    Sand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rel
    -0.31
    çĬĢ
    -0.29
    液ä½ĵ
    -0.28
    å®ŀçī©
    -0.27
     relic
    -0.26
     rebound
    -0.26
    è¡Įç¨ĭ
    -0.25
    çĭ¬
    -0.25
    åħ¥çĿ¡
    -0.24
     cycle
    -0.24
    POSITIVE LOGITS
    jong
    0.30
    Stra
    0.29
    etz
    0.28
    ernal
    0.27
    åłµ
    0.26
    orical
    0.26
     GetType
    0.25
    iou
    0.24
    è¶Ĭé«ĺ
    0.24
    æ´¾åĩº
    0.24
    Act Density 0.021%

    No Known Activations