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

    Neuronpedia

    INDEX
    Explanations

    Doctrine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Doctrine
    -1.20
     doctrine
    -1.06
    Doctrine
    -0.94
    doctrine
    -0.86
    MessageOf
    -0.67
     doctrines
    -0.67
    windowFixed
    -0.65
     Numerade
    -0.64
    MergeFrom
    -0.63
    expandindo
    -0.63
    POSITIVE LOGITS
    AddTagHelper
    0.63
    nofollow
    0.45
    sidenav
    0.42
     completo
    0.41
    AxisAlignment
    0.41
     complete
    0.40
    potranspiration
    0.40
    PyTuple
    0.39
    जर
    0.39
    }:${
    0.38
    Act Density 0.016%

    No Known Activations