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

    Neuronpedia

    INDEX
    Explanations

    Foreign abbreviations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (mail
    -0.07
    _ALLOW
    -0.07
     dislike
    -0.07
    ина
    -0.07
    Point
    -0.07
    _register
    -0.07
     furniture
    -0.06
    _adjust
    -0.06
     outlook
    -0.06
    _layout
    -0.06
    POSITIVE LOGITS
    ťan
    0.07
    ريكية
    0.07
    юр
    0.07
     OSD
    0.06
    estyle
    0.06
     Kata
    0.06
     Rockets
    0.06
     Propel
    0.06
    基金
    0.06
     Vz
    0.06
    Act Density 0.014%

    No Known Activations