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

    Neuronpedia

    INDEX
    Explanations

    language metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     middle
    0.40
     unic
    0.38
     Middles
    0.37
     different
    0.36
    UTO
    0.36
     whence
    0.36
     Ehr
    0.36
     ঘরে
    0.35
     successivo
    0.35
    ieten
    0.35
    POSITIVE LOGITS
     ايضا
    0.42
    也非常
    0.40
     επίσης
    0.36
    indazole
    0.36
     ながら
    0.36
     tidligere
    0.35
    돼
    0.35
     hefyd
    0.35
    arkt
    0.35
    Featuring
    0.34
    Act Density 0.021%

    No Known Activations