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

    Neuronpedia

    INDEX
    Explanations

    AI analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     foyer
    0.44
    онов
    0.42
    дает
    0.41
     fringes
    0.40
    험
    0.40
    <sup>
    0.39
    дей
    0.39
     examen
    0.38
     biv
    0.36
     firefighting
    0.36
    POSITIVE LOGITS
     ಕಾನೂ
    0.54
     ባህ
    0.53
     وک
    0.46
    IdleSync
    0.44
    LAGAB
    0.44
     এড়িয়ে
    0.44
     stessi
    0.44
    serialized
    0.44
    ച്ചു
    0.43
     اکث
    0.43
    Act Density 0.000%

    No Known Activations