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

    Neuronpedia

    INDEX
    Explanations

    arabic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ሎች
    0.39
    極
    0.39
    ပို့
    0.38
    かわらず
    0.38
    ),"
    0.37
    ុត
    0.37
    խ
    0.37
    ﺨ
    0.37
     wherever
    0.37
     Ende
    0.37
    POSITIVE LOGITS
    NODE
    0.41
    AME
    0.41
     древ
    0.39
    ﺐ
    0.39
    ائد
    0.38
     nodal
    0.38
    ادات
    0.38
    adeh
    0.37
    隔离
    0.37
    AIN
    0.36
    Act Density 0.002%

    No Known Activations