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

    Neuronpedia

    INDEX
    Explanations

    indexing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wang
    -0.07
     Tina
    -0.07
     fö
    -0.06
     positioned
    -0.06
     süt
    -0.06
     pra
    -0.06
     IAM
    -0.06
    Typ
    -0.06
     wander
    -0.06
     convolution
    -0.06
    POSITIVE LOGITS
    soc
    0.07
    Atomic
    0.07
     والإ
    0.07
     국가
    0.06
    	EIF
    0.06
    QueryString
    0.06
    ιας
    0.06
    /auto
    0.06
    薩
    0.06
    -minus
    0.06
    Act Density 0.212%

    No Known Activations