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

    Neuronpedia

    INDEX
    Explanations

    featuring attractive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    र
    0.51
    મ
    0.51
    м
    0.48
    嬛
    0.47
     année
    0.45
    ق
    0.45
    上映
    0.44
    ә
    0.44
    ર
    0.44
    ّر
    0.44
    POSITIVE LOGITS
     disruptions
    0.49
     jewel
    0.48
     fieldwork
    0.48
     undertakes
    0.47
     hypogly
    0.46
     wales
    0.46
     converts
    0.44
     تول
    0.44
     Practitioners
    0.44
     medics
    0.44
    Act Density 0.003%

    No Known Activations