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

    Neuronpedia

    INDEX
    Explanations

    Code/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -most
    -0.07
    nim
    -0.07
    (paths
    -0.07
    Directive
    -0.07
    _normal
    -0.07
    _bn
    -0.07
    ­های
    -0.06
     currentIndex
    -0.06
    xxx
    -0.06
     amat
    -0.06
    POSITIVE LOGITS
    xford
    0.08
    ONES
    0.06
    rf
    0.06
    iation
    0.06
    asa
    0.06
    YD
    0.06
     Myth
    0.06
    KEY
    0.06
     Lyrics
    0.05
     imprisoned
    0.05
    Act Density 0.001%

    No Known Activations