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

    Neuronpedia

    INDEX
    Explanations

    Code and general snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sm
    -0.53
    TRI
    -0.52
     Gough
    -0.52
    Tri
    -0.52
    to
    -0.52
    :"
    -0.51
    CCC
    -0.51
    mi
    -0.50
    tri
    -0.50
     tri
    -0.50
    POSITIVE LOGITS
    ThroughAttribute
    0.56
     TextAppearance
    0.56
    featureID
    0.55
    '},
    0.54
     CreateTagHelper
    0.54
    databind
    0.52
    tvguidetime
    0.51
     propOrder
    0.50
    sted
    0.48
     IBOutlet
    0.48
    Act Density 0.001%

    No Known Activations