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

    Neuronpedia

    INDEX
    Explanations

    dismiss or eliminate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    avantage
    0.38
     emphasized
    0.38
     hesitated
    0.38
    ទាំងអស់
    0.38
     moder
    0.37
    Asked
    0.37
     Glycer
    0.37
     Caen
    0.37
    inherit
    0.36
     রবি
    0.36
    POSITIVE LOGITS
     dismiss
    1.00
     elimin
    0.96
     dismissing
    0.95
     eliminate
    0.95
     dismissed
    0.95
    eliminate
    0.93
     dismissal
    0.93
     eliminated
    0.91
    Elim
    0.91
    elimin
    0.91
    Act Density 0.034%

    No Known Activations