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

    Neuronpedia

    INDEX
    Explanations

    weekly headlines, horoscopes, facts, jokes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endir
    0.84
    elung
    0.83
     Darstellung
    0.79
     definiert
    0.77
    odef
    0.77
    Leftrightarrow
    0.76
     eventually
    0.75
    を利用
    0.75
    何度も
    0.74
     Eventually
    0.74
    POSITIVE LOGITS
    Weekly
    1.75
     weekly
    1.74
     Weekly
    1.68
     오늘의
    1.61
     week
    1.59
     semanal
    1.54
     Spotlight
    1.51
     WEEK
    1.48
    오늘
    1.47
     Week
    1.45
    Act Density 0.193%

    No Known Activations