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

    Neuronpedia

    INDEX
    Explanations

    over time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nev
    -0.07
    法人
    -0.07
    Concurrency
    -0.07
    /compiler
    -0.07
    协会会长
    -0.07
    _null
    -0.07
     chu
    -0.07
    olvers
    -0.07
    initWith
    -0.07
    lius
    -0.06
    POSITIVE LOGITS
    意
    0.07
    rozen
    0.07
     -------↵
    0.07
     marks
    0.07
     turn
    0.07
    >&
    0.07
     vibr
    0.06
     Turn
    0.06
     Press
    0.06
     COR
    0.06
    Act Density 0.017%

    No Known Activations