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

    Neuronpedia

    INDEX
    Explanations

    cancel/close button actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     submit
    0.45
     submitted
    0.43
     reload
    0.41
    submit
    0.40
     shoot
    0.40
     sing
    0.40
    卜
    0.39
    ubmit
    0.39
     football
    0.38
    vaart
    0.38
    POSITIVE LOGITS
     Cancel
    1.49
     cancel
    1.45
     cancellations
    1.45
     cancellation
    1.44
    Cancel
    1.43
     canceling
    1.40
     cancels
    1.38
     cancelling
    1.37
     cancelled
    1.35
    cancel
    1.34
    Act Density 0.006%

    No Known Activations