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

    Neuronpedia

    INDEX
    Explanations

    calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     М
    -0.08
    Iraq
    -0.07
    -speed
    -0.07
    -filter
    -0.07
     savage
    -0.07
     calidad
    -0.07
    Dan
    -0.06
    atik
    -0.06
     m
    -0.06
     ($("#
    -0.06
    POSITIVE LOGITS
    272
    0.07
     留
    0.06
    addContainerGap
    0.06
    uncate
    0.06
    .Cursors
    0.06
    (labels
    0.06
    ZONE
    0.06
    ольно
    0.06
    771
    0.06
    175
    0.06
    Act Density 0.015%

    No Known Activations