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

    Neuronpedia

    INDEX
    Explanations

    phone/license plate numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (player
    -0.07
    再现
    -0.06
    UPI
    -0.06
    core
    -0.06
    波特
    -0.06
    ImagePath
    -0.06
     waters
    -0.06
    屁
    -0.06
     Polo
    -0.06
    罨
    -0.06
    POSITIVE LOGITS
    婶
    0.07
    rites
    0.07
    刳
    0.07
    _TRUNC
    0.07
    دينة
    0.07
    דק
    0.07
    _numero
    0.07
    PUT
    0.07
    דע
    0.07
     MAK
    0.07
    Act Density 0.074%

    No Known Activations