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

    Neuronpedia

    INDEX
    Explanations

    you have

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.90
    াত
    0.81
    ходи
    0.81
    ка
    0.81
    мени
    0.81
    кономи
    0.78
    ен
    0.78
    ו
    0.78
     económicos
    0.74
    دين
    0.74
    POSITIVE LOGITS
    u
    0.92
    σ
    0.91
     be
    0.89
    тся
    0.85
    ری
    0.84
    -->
    0.84
     can
    0.81
    տ
    0.81
    ע
    0.81
    an
    0.79
    Act Density 0.000%

    No Known Activations