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

    Neuronpedia

    INDEX
    Explanations

    possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ר
    0.75
    ر
    0.66
    ป
    0.61
    र
    0.54
    р
    0.54
    нус
    0.52
    ्यूटर
    0.52
    Cogn
    0.52
    ل
    0.51
    กด
    0.50
    POSITIVE LOGITS
    ischen
    0.49
    ischer
    0.46
    correlation
    0.46
     ponerse
    0.44
    ﯼ
    0.44
    ische
    0.43
    jecha
    0.42
    тами
    0.42
    shaders
    0.41
    yl
    0.41
    Act Density 0.000%

    No Known Activations