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

    Neuronpedia

    INDEX
    Explanations

    events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.76
     <=",
    -0.68
     Guel
    -0.66
    AndEndTag
    -0.65
     BoxFit
    -0.63
    Manbalar
    -0.63
    epam
    -0.63
    ⓧ
    -0.63
     препратки
    -0.60
    extAlignment
    -0.60
    POSITIVE LOGITS
    RegressionTest
    0.50
    Witam
    0.50
     Weather
    0.45
     WEATHER
    0.45
    Referencie
    0.43
    Weather
    0.40
    Koordin
    0.40
     lèvres
    0.40
     Briefing
    0.39
    moveToFirst
    0.39
    Act Density 0.014%

    No Known Activations