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

    Neuronpedia

    INDEX
    Explanations

    disclaimer text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    0.53
     أثناء
    0.51
    ق
    0.50
     그는
    0.50
    িমা
    0.50
    énergie
    0.49
    월
    0.47
     bedeutet
    0.47
    प्रधानमंत्री
    0.46
     에너지
    0.46
    POSITIVE LOGITS
     considere
    0.59
     Godfather
    0.58
     mercenary
    0.57
     grudge
    0.55
     moim
    0.55
     я
    0.55
    自分が
    0.54
     myself
    0.52
     reputed
    0.52
    foaf
    0.52
    Act Density 0.004%

    No Known Activations