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

    Neuronpedia

    INDEX
    Explanations

    statistical analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     asphalt
    -0.09
     afect
    -0.08
    彻
    -0.08
     vtk
    -0.08
    gar
    -0.08
    apolis
    -0.08
     afflicted
    -0.08
     misinformation
    -0.08
    553
    -0.08
    abra
    -0.08
    POSITIVE LOGITS
     konnen
    0.10
     anticipating
    0.08
     количе
    0.08
     predefined
    0.08
     другу
    0.08
    lex
    0.08
     вс
    0.08
     predetermined
    0.08
     निय
    0.08
    Reporting
    0.08
    Act Density 0.003%

    No Known Activations