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

    Neuronpedia

    INDEX
    Explanations

    cancellation/reduction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (View
    -0.08
     ihtiyaç
    -0.07
     multif
    -0.07
     부족
    -0.07
     isan
    -0.07
    umbuhan
    -0.07
     Помимо
    -0.07
     farming
    -0.07
     dreamy
    -0.07
     personality
    -0.07
    POSITIVE LOGITS
     cancel
    0.17
     canc
    0.16
     cancelling
    0.15
     canceled
    0.14
     cancellation
    0.14
     Cancel
    0.14
     Canc
    0.14
    cancel
    0.14
    	cancel
    0.13
     CANCEL
    0.13
    Act Density 0.013%

    No Known Activations