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

    Neuronpedia

    INDEX
    Explanations

    translation and languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sprocket
    0.38
     drivetrain
    0.36
     owning
    0.35
     sprint
    0.35
     triad
    0.35
    heast
    0.35
    ashmir
    0.34
     stripper
    0.34
     दिग्विजय
    0.34
     waveguides
    0.34
    POSITIVE LOGITS
     영어
    2.08
     translated
    2.03
    日本語
    1.97
     English
    1.92
     Translated
    1.88
     translation
    1.86
     Türkçe
    1.86
    translated
    1.85
    英文
    1.83
    英語
    1.82
    Act Density 0.052%

    No Known Activations