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

    Neuronpedia

    INDEX
    Explanations

    Japanese text and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .font
    -0.07
    ['__
    -0.07
    /tmp
    -0.07
    ilib
    -0.07
    coming
    -0.07
     Pant
    -0.07
    帳號
    -0.07
     Amend
    -0.06
     OAuth
    -0.06
    getTitle
    -0.06
    POSITIVE LOGITS
     Sleep
    0.06
    evity
    0.06
    高等教育
    0.06
    rows
    0.06
    0.06
    row
    0.06
    ((&
    0.06
    进程
    0.06
    ۋ
    0.06
    achinery
    0.06
    Act Density 0.042%

    No Known Activations