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

    Neuronpedia

    INDEX
    Explanations

    dependencies and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enzione
    0.86
    鳟
    0.85
     stipulates
    0.79
    цени
    0.77
    kuensi
    0.75
    abell
    0.74
    elijk
    0.73
     eenvoudig
    0.72
    ধারা
    0.72
     ክፍል
    0.72
    POSITIVE LOGITS
     anam
    0.88
     많은
    0.82
    我
    0.79
     Nevertheless
    0.79
     신
    0.79
    果然
    0.78
     σημαν
    0.78
     Murder
    0.78
     حين
    0.77
     সন্তান
    0.76
    Act Density 0.000%

    No Known Activations