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

    Neuronpedia

    INDEX
    Explanations

    Retirement Now

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     இறுதியில்
    0.47
     রেখেছে
    0.45
     uiteindelijk
    0.44
     schließlich
    0.43
     आखिरकार
    0.42
     plupart
    0.42
    ্তির
    0.42
     acaba
    0.41
     pourrait
    0.41
     renormalized
    0.40
    POSITIVE LOGITS
     alienation
    0.45
    0
    0.44
    н
    0.44
     misunderstand
    0.41
    ہ
    0.40
    ٹ
    0.40
    د
    0.39
    ड़क
    0.38
    ற்ற
    0.38
    n
    0.38
    Act Density 0.016%

    No Known Activations