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

    Neuronpedia

    INDEX
    Explanations

    forum posts/advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Wh
    -0.08
     marriage
    -0.07
    ricanes
    -0.07
     mej
    -0.07
    挥发
    -0.07
    /↵
    -0.07
    꾜
    -0.06
    .Func
    -0.06
    -Feb
    -0.06
    洗干净
    -0.06
    POSITIVE LOGITS
    דבק
    0.07
    装备
    0.07
     Oswald
    0.07
     STACK
    0.07
     искус
    0.07
    بعث
    0.07
    堆
    0.06
    tone
    0.06
     כפי
    0.06
     flow
    0.06
    Act Density 0.277%

    No Known Activations