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

    Neuronpedia

    INDEX
    Explanations

    even possibly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     무엇
    0.34
     unmistakable
    0.33
     dependable
    0.33
    omonas
    0.32
     সমস্ত
    0.32
    ="";
    0.32
     সর্বদা
    0.32
     نمی‌
    0.32
     পাকিস্তানীদের
    0.32
    that
    0.32
    POSITIVE LOGITS
     sogar
    0.96
     zelfs
    0.92
    甚至
    0.87
     addirittura
    0.79
     incluso
    0.77
     навіть
    0.77
     thậm
    0.77
     även
    0.75
    甚至是
    0.75
     bahkan
    0.75
    Act Density 0.222%

    No Known Activations