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

    Neuronpedia

    INDEX
    Explanations

    features

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     of
    -0.08
    =<?=$
    -0.07
     by
    -0.07
     with
    -0.07
    /pg
    -0.07
     Boyd
    -0.07
     Disneyland
    -0.06
     Winn
    -0.06
    .NumericUpDown
    -0.06
     bicycle
    -0.06
    POSITIVE LOGITS
     features
    0.08
    Ports
    0.08
     feature
    0.07
    features
    0.07
     sector
    0.07
    индивид
    0.07
    _Header
    0.07
     Vendor
    0.07
    .vert
    0.07
    ינים
    0.07
    Act Density 0.044%

    No Known Activations