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

    Neuronpedia

    INDEX
    Explanations

    eu

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _registers
    -0.07
     comfort
    -0.06
     serum
    -0.06
     Moor
    -0.06
    Premium
    -0.06
     FileAccess
    -0.06
     beaches
    -0.06
     potency
    -0.06
     Inner
    -0.06
    ่ม
    -0.06
    POSITIVE LOGITS
    оск
    0.08
    reads
    0.07
    _sep
    0.07
    我们
    0.07
    وري
    0.07
    اني
    0.06
    ź
    0.06
    يع
    0.06
    쟁
    0.06
     التر
    0.06
    Act Density 0.073%

    No Known Activations