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

    Neuronpedia

    INDEX
    Explanations

    Value of business terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     overseeing
    0.40
     indebted
    0.39
    操作系统
    0.38
    नांतर
    0.38
     YouTube
    0.38
     एक्सपर्ट
    0.37
     ২০১৯
    0.37
    ărat
    0.36
     ২০২২
    0.36
    网红
    0.36
    POSITIVE LOGITS
     foci
    0.46
     ܗܘ
    0.42
     squiggle
    0.42
     per
    0.40
     repetition
    0.40
     "~
    0.39
    だが
    0.39
    ит
    0.39
    銭
    0.39
     kř
    0.38
    Act Density 0.002%

    No Known Activations