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

    Neuronpedia

    INDEX
    Explanations

    abstract qualities and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     കഥ
    0.67
     වර්ග
    0.66
    orithm
    0.64
     处理
    0.63
    webserv
    0.63
     লাশ
    0.63
    utiva
    0.61
    Costs
    0.61
    复杂的
    0.59
     зарабо
    0.58
    POSITIVE LOGITS
     transparency
    2.21
     homogeneity
    2.16
     stability
    2.15
     uniformity
    2.03
     honesty
    2.03
     simplicity
    2.02
     humility
    1.98
     impartiality
    1.98
     integrity
    1.92
     flexibility
    1.91
    Act Density 0.543%

    No Known Activations