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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manages
    -0.06
    iển
    -0.06
    chsel
    -0.06
    Bang
    -0.06
     Cleaner
    -0.06
    Silver
    -0.06
    sections
    -0.06
     departamento
    -0.06
    “The
    -0.06
    近
    -0.06
    POSITIVE LOGITS
     ruby
    0.07
     fx
    0.06
    ports
    0.06
    Ю
    0.06
     个
    0.06
    ￥
    0.06
     اکتبر
    0.06
     tarihinde
    0.06
    ！");↵
    0.06
    pname
    0.06
    Act Density 0.001%

    No Known Activations