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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الخاص
    0.93
    ش
    0.91
    ิน
    0.89
     photonic
    0.87
    ாதை
    0.86
    AW
    0.83
     glandular
    0.83
     ^{
    0.83
    を楽し
    0.82
     आईआई
    0.82
    POSITIVE LOGITS
    пример
    0.64
     इमरजेंसी
    0.63
    families
    0.62
     Ngo
    0.61
     vecchia
    0.61
    岷
    0.61
    jač
    0.60
    lüğ
    0.60
    но
    0.59
     Sein
    0.59
    Act Density 0.001%

    No Known Activations