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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Script
    -0.06
    ,val
    -0.06
     aren
    -0.06
    EM
    -0.06
    egree
    -0.06
    шибка
    -0.06
     Bengals
    -0.06
    axies
    -0.06
     bach
    -0.06
    их
    -0.06
    POSITIVE LOGITS
     To
    0.08
     hlavní
    0.07
    ashtra
    0.07
    to
    0.07
     to
    0.06
     backbone
    0.06
    „D
    0.06
    	
↵
    0.06
     lov
    0.06
     attravers
    0.06
    Act Density 0.014%

    No Known Activations