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

    Neuronpedia

    INDEX
    Explanations

    ////////////////////////////////////////////////////////////////////////////

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rou
    -0.07
    stery
    -0.07
     Baldwin
    -0.06
     중
    -0.06
     EVE
    -0.06
    Wrap
    -0.06
    _lm
    -0.06
     mall
    -0.06
     restart
    -0.06
    \:
    -0.06
    POSITIVE LOGITS
     Innov
    0.08
    works
    0.07
    exampleInputEmail
    0.07
    feeding
    0.07
     cancelButtonTitle
    0.07
    oğ
    0.07
    Information
    0.07
    neath
    0.06
     kèm
    0.06
     Flooring
    0.06
    Act Density 0.001%

    No Known Activations