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

    Neuronpedia

    INDEX
    Explanations

    code assignment or definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    این
    0.68
    สำหรับ
    0.64
    كيف
    0.64
    ↵
    0.57
    larda
    0.57
    ный
    0.56
    ۔
    0.56
    两
    0.56
    rün
    0.55
    ного
    0.54
    POSITIVE LOGITS
    il
    0.70
    K
    0.60
    е
    0.57
    en
    0.55
     K
    0.55
     el
    0.55
     n
    0.51
    B
    0.50
     S
    0.49
    S
    0.49
    Act Density 0.009%

    No Known Activations