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

    Neuronpedia

    INDEX
    Explanations

    character prompts asking for Name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dealing
    0.41
    商品を
    0.41
    bark
    0.40
    fluoro
    0.39
    form
    0.38
    fol
    0.38
    바
    0.38
    ード
    0.38
    anny
    0.38
    feeding
    0.38
    POSITIVE LOGITS
     associa
    0.50
    年龄
    0.49
     ആരംഭ
    0.49
    接著
    0.49
     aged
    0.49
     الرسم
    0.48
     الشر
    0.48
     Ska
    0.48
     الم
    0.47
     aprendizaje
    0.47
    Act Density 0.001%

    No Known Activations