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

    Neuronpedia

    INDEX
    Explanations

    time loops

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -inline
    -0.08
     الموقع
    -0.08
     mobiele
    -0.08
    менты
    -0.07
    (optional
    -0.07
    ilh
    -0.07
    ستر
    -0.07
    -demo
    -0.07
     onderhouden
    -0.07
    ството
    -0.07
    POSITIVE LOGITS
     repetitive
    0.16
     endlessly
    0.15
     repetition
    0.14
    重复
    0.14
     repeating
    0.14
     repetitions
    0.14
     반복
    0.14
     endless
    0.13
     repet
    0.13
     intermin
    0.13
    Act Density 0.031%

    No Known Activations