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

    Neuronpedia

    INDEX
    Explanations

    end of words or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ol
    0.34
    ్యాన్ని
    0.33
    ভাবে
    0.31
    ಗಳನ್ನು
    0.30
     হইতেছিল
    0.30
    _{
    0.29
    á
    0.29
    ित
    0.29
     করিতেছিল
    0.29
    ทั้งหมด
    0.29
    POSITIVE LOGITS
    ك
    0.39
     exempel
    0.37
     an
    0.36
     the
    0.35
     พ
    0.35
     fixa
    0.34
    드
    0.34
     ه
    0.33
     this
    0.33
     Egipto
    0.33
    Act Density 1.941%

    No Known Activations