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

    Neuronpedia

    INDEX
    Explanations

    how to form questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ảo
    0.44
    ️⃣
    0.40
    མ་
    0.39
    ቂ
    0.39
    =='
    0.39
    )="
    0.39
    0.39
    UsedError
    0.38
    odym
    0.38
     genealogical
    0.38
    POSITIVE LOGITS
    р
    0.70
    мо
    0.57
     experimentos
    0.56
    ر
    0.55
     dene
    0.54
    под
    0.51
     liger
    0.51
    Под
    0.49
    Ко
    0.49
    по
    0.49
    Act Density 0.001%

    No Known Activations