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

    Neuronpedia

    INDEX
    Explanations

    concentrate power

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಕ್ಷ
    0.41
     sicherlich
    0.41
    şi
    0.37
     nous
    0.37
     podemos
    0.37
     Dae
    0.37
    Indianapolis
    0.37
    characterized
    0.36
    کیا
    0.36
    ধা
    0.35
    POSITIVE LOGITS
     일부
    0.40
    étricas
    0.38
     листь
    0.37
     вовсе
    0.37
     шер
    0.36
    ϱ
    0.36
     слегка
    0.36
     საჭ
    0.36
    [(
    0.35
    一丝
    0.35
    Act Density 0.001%

    No Known Activations