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

    Neuronpedia

    INDEX
    Explanations

    Code or math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /version
    -0.07
     apologize
    -0.07
    /input
    -0.07
    /'.$
    -0.07
    com
    -0.06
     generating
    -0.06
    คาส
    -0.06
     Charges
    -0.06
    [args
    -0.06
    reshold
    -0.06
    POSITIVE LOGITS
     forgiveness
    0.06
    编辑
    0.06
    γή
    0.06
     krás
    0.06
    GY
    0.06
     بندی
    0.06
    El
    0.06
    	move
    0.06
     Est
    0.06
     sooner
    0.06
    Act Density 0.004%

    No Known Activations