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

    Neuronpedia

    INDEX
    Explanations

    decluttering and organizing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Admiral
    -0.07
     disco
    -0.07
     rows
    -0.07
    達
    -0.06
    टन
    -0.06
    -with
    -0.06
    uckets
    -0.06
    Main
    -0.06
    Bits
    -0.06
    iances
    -0.06
    POSITIVE LOGITS
     امتی
    0.07
    (startTime
    0.07
    _IMETHOD
    0.06
    DATE
    0.06
    ifferent
    0.06
    ventory
    0.06
     Vertex
    0.06
     Instrument
    0.06
     './../../
    0.06
     Stadt
    0.06
    Act Density 0.052%

    No Known Activations