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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     constantemente
    0.60
     đem
    0.60
     ने
    0.59
     দিয়ে
    0.59
     constantly
    0.58
    頗
    0.58
     постоянно
    0.57
    แค
    0.55
    带着
    0.55
    帶著
    0.54
    POSITIVE LOGITS
     SHOULD
    0.64
    erdale
    0.63
     róż
    0.62
    chrane
    0.59
     යුතු
    0.58
    écart
    0.58
     আবির্ভাব
    0.58
    malı
    0.57
     발전
    0.57
    ོང་
    0.56
    Act Density 0.000%

    No Known Activations