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

    Neuronpedia

    INDEX
    Explanations

    respect to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     riddle
    0.92
     שם
    0.88
     dadurch
    0.86
     Roughly
    0.85
     whims
    0.83
     Enemies
    0.81
     kahi
    0.81
     عندي
    0.80
     punya
    0.79
     Мне
    0.79
    POSITIVE LOGITS
    ively
    1.10
    icularly
    0.95
    respect
    0.89
    standing
    0.88
    ያንዳንዱ
    0.84
    ignes
    0.84
    信息公示
    0.83
    ourism
    0.83
    otoxin
    0.82
    ure
    0.82
    Act Density 0.017%

    No Known Activations