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

    Neuronpedia

    INDEX
    Explanations

    documentation examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    อก
    0.38
     Ent
    0.38
     quantas
    0.36
     Ric
    0.36
     Modular
    0.35
     Module
    0.35
    ぜ
    0.35
    module
    0.35
    dashboard
    0.35
     Durante
    0.34
    POSITIVE LOGITS
     ઓફ
    0.44
     getMain
    0.39
     નિય
    0.38
    uksia
    0.38
     النصوص
    0.38
     کیف
    0.37
    त्रेयी
    0.37
    薦
    0.37
    规
    0.36
     vých
    0.36
    Act Density 0.001%

    No Known Activations