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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    گانی
    -0.07
    Successful
    -0.07
    Pretty
    -0.07
    	IN
    -0.06
    DIM
    -0.06
     supplemented
    -0.06
    -circle
    -0.06
    versed
    -0.06
    .Size
    -0.06
    vey
    -0.06
    POSITIVE LOGITS
    刷
    0.08
     THESE
    0.07
    �
    0.07
    RETURN
    0.07
    헌
    0.07
    燕
    0.06
     taxp
    0.06
     newText
    0.06
     zeit
    0.06
    .ul
    0.06
    Act Density 0.098%

    No Known Activations