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

    Neuronpedia

    INDEX
    Explanations

    control systems and stability

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,',
    -0.07
     odstran
    -0.07
     preparation
    -0.06
     stabilization
    -0.06
    acio
    -0.06
     vững
    -0.06
     deactivated
    -0.06
     Liverpool
    -0.06
    ۲۲
    -0.06
     Bethlehem
    -0.06
    POSITIVE LOGITS
    ']])↵
    0.07
     Resolve
    0.07
    카지노
    0.07
     municipalities
    0.06
     ske
    0.06
    _school
    0.06
    専
    0.06
    сок
    0.06
    .sd
    0.06
    _FEED
    0.06
    Act Density 0.014%

    No Known Activations