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

    Neuronpedia

    INDEX
    Explanations

    Legal/technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sw
    -0.07
     wag
    -0.07
    Saturday
    -0.06
     Nar
    -0.06
    學院
    -0.06
     كتب
    -0.06
    CAM
    -0.06
    �
    -0.06
    원
    -0.06
    Forum
    -0.06
    POSITIVE LOGITS
     ilgi
    0.08
    	flag
    0.07
     янва
    0.07
    	tile
    0.07
    /control
    0.07
    !!
    0.06
    ViewState
    0.06
     Large
    0.06
     indian
    0.06
    .Cursor
    0.06
    Act Density 0.000%

    No Known Activations