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

    Neuronpedia

    INDEX
    Explanations

    to help me decide better

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     рано
    0.70
    提供了
    0.68
     предостав
    0.66
    Providing
    0.65
    providing
    0.65
    提取
    0.64
     förm
    0.63
    énération
    0.62
    діть
    0.62
    Ừ
    0.61
    POSITIVE LOGITS
     best
    0.93
     decide
    0.91
     deciding
    0.90
     decided
    0.87
     decides
    0.86
     better
    0.86
     mieux
    0.86
     gauge
    0.85
     melhor
    0.84
     decidir
    0.81
    Act Density 0.083%

    No Known Activations