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

    Neuronpedia

    INDEX
    Explanations

    "what is"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    درا
    0.64
    loro
    0.58
     الام
    0.56
    塘
    0.54
    مثل
    0.52
     perdido
    0.51
    چنین
    0.51
     older
    0.51
     FIXME
    0.50
    ከተ
    0.50
    POSITIVE LOGITS
    ε
    0.68
     NgModule
    0.61
    ्रेडिट
    0.59
    ना
    0.59
    ｅ
    0.58
    💬
    0.57
    ש
    0.56
    ен
    0.56
    elle
    0.55
    ы
    0.55
    Act Density 0.605%

    No Known Activations