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

    Neuronpedia

    INDEX
    Explanations

    Gemma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     impianti
    0.39
     Modell
    0.38
    '),('
    0.37
    érêt
    0.36
     Craft
    0.35
    یمپ
    0.35
     crafts
    0.35
     విస్త
    0.35
     pm
    0.35
     griech
    0.35
    POSITIVE LOGITS
    Re
    0.43
     டீ
    0.42
    டிக
    0.40
    モーニング
    0.38
    deep
    0.38
     Tentang
    0.38
    rub
    0.37
    Тем
    0.37
     bram
    0.37
     ре
    0.36
    Act Density 0.029%

    No Known Activations