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

    Neuronpedia

    INDEX
    Explanations

    ** * ** : text formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝐊
    0.39
     nyata
    0.39
     stvarn
    0.38
     কৃতজ্ঞ
    0.38
    âmica
    0.37
    ximation
    0.37
     comprehensive
    0.37
    質感
    0.36
     zusamm
    0.36
     İlç
    0.35
    POSITIVE LOGITS
    婀
    0.38
    upp
    0.38
    én
    0.37
     Char
    0.37
    ieno
    0.37
     compensates
    0.36
     upp
    0.36
     blaze
    0.35
    itio
    0.34
     නොව
    0.34
    Act Density 0.000%

    No Known Activations