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

    Neuronpedia

    INDEX
    Explanations

    lack or not enough

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perdido
    0.76
    vore
    0.73
     потеря
    0.72
     perdida
    0.72
    on
    0.71
    هن
    0.68
    ২৫
    0.68
     dropped
    0.68
     perguntas
    0.68
     misconceptions
    0.67
    POSITIVE LOGITS
    足够的
    1.06
    任何
    1.01
     adequate
    0.90
     adequately
    0.89
    十分に
    0.88
    any
    0.88
     ausreiche
    0.88
    丝毫
    0.88
     पर्याप्त
    0.85
     suficiente
    0.84
    Act Density 0.295%

    No Known Activations