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

    Neuronpedia

    INDEX
    Explanations

    Hebrew and Arabic words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lla
    0.50
    LLA
    0.42
    ◢
    0.40
    ños
    0.40
    pta
    0.39
    pto
    0.39
    пто
    0.39
    ptor
    0.39
     gstlal
    0.39
    lls
    0.39
    POSITIVE LOGITS
    âr
    0.42
    ﺟ
    0.39
    ائج
    0.39
    যার
    0.39
    іл
    0.38
    ז
    0.38
    גר
    0.36
     رحم
    0.36
    ני
    0.36
    য়ার
    0.36
    Act Density 0.001%

    No Known Activations