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

    Neuronpedia

    INDEX
    Explanations

    remove/cancel/discard

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inconven
    0.60
     लापर
    0.50
     inconvenience
    0.50
     infrequently
    0.50
     Loss
    0.48
     น้อย
    0.48
     குறைவாக
    0.47
     tổn
    0.47
     indiscrimin
    0.47
    Loss
    0.46
    POSITIVE LOGITS
     scrapped
    1.48
     abort
    1.42
     aborted
    1.38
     abandoned
    1.36
     cancelled
    1.34
    abort
    1.34
     abandon
    1.32
     scrap
    1.31
     cancel
    1.30
     discarded
    1.30
    Act Density 0.528%

    No Known Activations