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

    Neuronpedia

    INDEX
    Explanations

    is King / Key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     различные
    0.88
    このような
    0.86
    非常的
    0.78
     বিভিন্ন
    0.76
     Cual
    0.75
     বৎসরের
    0.75
     دوسرے
    0.75
     Bereich
    0.74
     ૩
    0.73
     discussed
    0.73
    POSITIVE LOGITS
     😉
    1.15
    ™.
    1.12
    !:
    1.05
     ;)
    1.04
    ™
    1.03
    ™,
    1.01
     😏
    0.99
    ®,
    0.93
    !.
    0.92
    But
    0.89
    Act Density 0.083%

    No Known Activations