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

    Neuronpedia

    INDEX
    Explanations

    Code/Data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enjoyed
    -0.07
     info
    -0.07
     SYMBOL
    -0.07
     CARD
    -0.06
     Dest
    -0.06
     Thermal
    -0.06
     SPEC
    -0.06
     pandemic
    -0.06
     prepar
    -0.06
    스터
    -0.06
    POSITIVE LOGITS
     úrov
    0.07
    llib
    0.07
    خی
    0.06
    ôm
    0.06
    融
    0.06
    ौद
    0.06
    _xs
    0.06
     unwitting
    0.06
    áli
    0.06
    讯
    0.06
    Act Density 0.006%

    No Known Activations