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

    Neuronpedia

    INDEX
    Explanations

    copyright and reproduction restrictions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jud
    -0.07
    须
    -0.07
    侃
    -0.07
     Hung
    -0.07
    _POP
    -0.07
    葡萄
    -0.07
    枇
    -0.07
    expl
    -0.07
     typ
    -0.07
    耜
    -0.06
    POSITIVE LOGITS
    Equality
    0.07
    胎儿
    0.07
     المتعل
    0.07
     helfen
    0.07
     arbe
    0.07
     האדם
    0.07
    etre
    0.07
    מחיר
    0.07
    ציל
    0.07
     shorter
    0.06
    Act Density 0.004%

    No Known Activations