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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Staffing
    -0.08
    考
    -0.08
     ಸಿಬ್ಬಂದ
    -0.08
     nhau
    -0.08
     bishops
    -0.07
     Filtering
    -0.07
     butterflies
    -0.07
     ingress
    -0.07
    -Level
    -0.07
     �
    -0.07
    POSITIVE LOGITS
    ну
    0.08
    integer
    0.08
     gern
    0.08
    mittelt
    0.08
     المجتمع
    0.08
     sean
    0.08
    _integer
    0.08
     politely
    0.08
    .integer
    0.08
     सुन
    0.08
    Act Density 0.003%

    No Known Activations