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

    Neuronpedia

    INDEX
    Explanations

    some

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Japan
    -0.07
     beat
    -0.07
    EQ
    -0.07
     Bail
    -0.06
     mozilla
    -0.06
     پیش
    -0.06
     participates
    -0.06
     aile
    -0.06
    MapView
    -0.06
    -bound
    -0.06
    POSITIVE LOGITS
    系列
    0.07
    .server
    0.06
     contrace
    0.06
    .ShowDialog
    0.06
     Snapchat
    0.06
    .BO
    0.06
     advisory
    0.06
     країни
    0.06
    0.06
     nar
    0.06
    Act Density 0.033%

    No Known Activations