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

    Neuronpedia

    INDEX
    Explanations

    days of the week

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spur
    -0.07
    Presence
    -0.07
    我们
    -0.07
     cancer
    -0.07
    地球
    -0.07
     quitting
    -0.06
     userList
    -0.06
     région
    -0.06
     unab
    -0.06
    いの
    -0.06
    POSITIVE LOGITS
     ευ
    0.06
     Hermes
    0.06
    icans
    0.06
    nants
    0.06
     Kurds
    0.06
    Psych
    0.06
    _refer
    0.06
     bağlı
    0.06
    SCREEN
    0.06
     HOWEVER
    0.06
    Act Density 0.003%

    No Known Activations