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

    Neuronpedia

    INDEX
    Explanations

    language model understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uksi
    0.89
    Ссылки
    0.79
    (!(
    0.78
    ровать
    0.78
     Winkel
    0.77
     fény
    0.77
    joner
    0.76
    க்கை
    0.75
    करा
    0.75
    λαν
    0.75
    POSITIVE LOGITS
     spoken
    1.03
     Speaking
    0.93
     Bari
    0.91
     Wikipédia
    0.89
    Speaking
    0.88
    ローブ
    0.88
     pathologists
    0.87
    zinha
    0.86
     ట
    0.84
    Herd
    0.83
    Act Density 0.688%

    No Known Activations