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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LNG
    -0.06
     vět
    -0.06
    ary
    -0.06
     Clarkson
    -0.06
    esign
    -0.06
     Db
    -0.06
    .am
    -0.06
    ادة
    -0.06
    ुष
    -0.06
    ुल
    -0.06
    POSITIVE LOGITS
     Drain
    0.08
     mains
    0.07
     proposals
    0.07
     заг
    0.07
     tông
    0.06
     Laser
    0.06
    iless
    0.06
     Shapes
    0.06
    _drag
    0.06
    -model
    0.06
    Act Density 0.001%

    No Known Activations