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

    Neuronpedia

    INDEX
    Explanations

    company names and people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ายเป็น
    0.34
     jako
    0.34
    ål
    0.34
     esistono
    0.33
    ův
    0.33
     whose
    0.33
    Buff
    0.33
    хай
    0.32
    儘
    0.31
     jonka
    0.31
    POSITIVE LOGITS
     어머니
    0.35
     خوات
    0.32
     스스로
    0.32
     বাছাই
    0.29
    0.29
     farewell
    0.29
     CheckException
    0.28
     მხ
    0.28
     CORPER
    0.27
     prologue
    0.27
    Act Density 0.023%

    No Known Activations