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

    Neuronpedia

    INDEX
    Explanations

    e

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     setData
    -0.07
    萬
    -0.07
     Noticed
    -0.07
    .Board
    -0.07
     squares
    -0.06
    “My
    -0.06
     REPORT
    -0.06
    “The
    -0.06
     стол
    -0.06
     Maze
    -0.06
    POSITIVE LOGITS
     дисцип
    0.06
    	pc
    0.06
     charisma
    0.06
     генера
    0.06
     애
    0.06
    .CodeAnalysis
    0.06
     seri
    0.06
    scope
    0.06
     odv
    0.06
    RING
    0.06
    Act Density 0.012%

    No Known Activations