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

    Neuronpedia

    INDEX
    Explanations

    numbers and percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Opening
    -0.08
     gaussian
    -0.07
     valide
    -0.07
    employer
    -0.07
    Beyond
    -0.07
    Lab
    -0.07
     Lease
    -0.06
     Iran
    -0.06
    Borders
    -0.06
     Judge
    -0.06
    POSITIVE LOGITS
    :"",↵
    0.06
    _Timer
    0.06
    ７
    0.06
    `='$
    0.06
    _image
    0.06
    相手
    0.06
     anarch
    0.06
    dex
    0.06
     ")";↵
    0.06
    .spawn
    0.06
    Act Density 0.049%

    No Known Activations