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

    Neuronpedia

    INDEX
    Explanations

    URL and code issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    solve
    -0.07
     Begin
    -0.07
     boils
    -0.06
    IES
    -0.06
    -degree
    -0.06
    Grid
    -0.06
     confession
    -0.06
    ував
    -0.06
    _AREA
    -0.06
     organization
    -0.06
    POSITIVE LOGITS
    oueur
    0.06
    닥
    0.06
    .tagName
    0.06
    	player
    0.06
    .classList
    0.06
     tpl
    0.06
     num
    0.06
     적용
    0.06
     вес
    0.06
     asker
    0.06
    Act Density 0.043%

    No Known Activations