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

    Neuronpedia

    INDEX
    Explanations

    common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     heap
    -0.07
    BV
    -0.07
    D
    -0.07
    categories
    -0.07
    。
    -0.07
    apr
    -0.07
    "w
    -0.07
    Account
    -0.07
    _dynamic
    -0.07
     competit
    -0.07
    POSITIVE LOGITS
     ביק
    0.08
    (SQLException
    0.07
    혹
    0.07
    ...',↵
    0.07
     спец
    0.07
    湘西
    0.06
     kidd
    0.06
    日起
    0.06
    Opening
    0.06
     Folk
    0.06
    Act Density 0.279%

    No Known Activations