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

    Neuronpedia

    INDEX
    Explanations

    remove or eliminate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    লাগ
    0.72
     آنے
    0.71
     Verbesser
    0.71
    ouncy
    0.68
    ိုင်
    0.68
     peningkatan
    0.67
    တည်
    0.67
     దో
    0.65
     calon
    0.64
    穩
    0.64
    POSITIVE LOGITS
     removal
    2.53
     remove
    2.51
     removed
    2.48
     eliminated
    2.41
     removing
    2.40
     eliminate
    2.32
    remove
    2.28
     Remove
    2.27
    Remove
    2.25
     abandoning
    2.24
    Act Density 2.041%

    No Known Activations