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

    Neuronpedia

    INDEX
    Explanations

    and I want to acknowledge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Notwithstanding
    0.80
    Notwithstanding
    0.75
     Despite
    0.73
     enjoying
    0.70
     consistent
    0.66
     positive
    0.65
     During
    0.65
     notwithstanding
    0.64
     sufficiently
    0.64
     very
    0.64
    POSITIVE LOGITS
    Payload
    0.89
     slogans
    0.81
     Tricks
    0.76
     Anbieter
    0.76
     lettering
    0.75
     Receipts
    0.75
    ఫ్‌
    0.74
     rookies
    0.73
     gadgets
    0.72
    ifact
    0.72
    Act Density 0.057%

    No Known Activations