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

    Neuronpedia

    INDEX
    Explanations

    topics and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rech
    0.78
    ρ
    0.75
     sidan
    0.75
    olese
    0.72
     پای
    0.72
    ığı
    0.72
     suivant
    0.72
     even
    0.71
    isma
    0.71
     artes
    0.70
    POSITIVE LOGITS
     провели
    0.86
     System
    0.84
     Improve
    0.81
     Цвет
    0.80
     Treasurer
    0.80
     Release
    0.79
     Karriere
    0.79
     Maintenant
    0.79
     повинні
    0.79
     Agora
    0.78
    Act Density 0.000%

    No Known Activations