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

    Neuronpedia

    INDEX
    Explanations

    Time indexing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adir
    -0.07
    SP
    -0.07
    Directory
    -0.07
    ernes
    -0.06
    >↵↵
    -0.06
     prepaid
    -0.06
     paradigm
    -0.06
     Value
    -0.06
    adı
    -0.06
    数据
    -0.06
    POSITIVE LOGITS
    isex
    0.07
     фин
    0.07
     можно
    0.07
    "%
    0.06
     Pere
    0.06
    _palette
    0.06
    (Function
    0.06
     disconnected
    0.06
    \'
    0.06
    xce
    0.06
    Act Density 0.014%

    No Known Activations