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

    Neuronpedia

    INDEX
    Explanations

    defects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onte
    -0.48
     event
    -0.48
    参
    -0.46
    ಿಕ
    -0.45
     detik
    -0.45
    يادة
    -0.45
    沛
    -0.45
    neurial
    -0.45
     you
    -0.44
     ending
    -0.44
    POSITIVE LOGITS
    MLLoader
    0.87
    Personensuche
    0.86
     GIPHY
    0.84
    RTEX
    0.82
    IsContent
    0.80
    WriteBarrier
    0.78
    #+#
    0.77
     صوتيه
    0.75
     disambiguazione
    0.74
    bootstrapcdn
    0.73
    Act Density 0.021%

    No Known Activations