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

    Neuronpedia

    INDEX
    Explanations

    walking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     outside
    -0.08
    -notification
    -0.06
    ,
↵
↵
    -0.06
     commentator
    -0.06
     Census
    -0.06
    _OVER
    -0.06
    动
    -0.06
     youngest
    -0.06
    들이
    -0.06
     Occupational
    -0.06
    POSITIVE LOGITS
     사항
    0.07
    ünd
    0.07
     Prel
    0.07
    _REST
    0.06
     انواع
    0.06
    ackbar
    0.06
     initData
    0.06
    (?:
    0.06
     Hind
    0.06
     Dana
    0.06
    Act Density 0.038%

    No Known Activations