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

    Neuronpedia

    INDEX
    Explanations

    responses after punctuation or "with"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mantuvo
    0.90
    al
    0.89
     LPG
    0.89
    ⁣
    0.89
     tincture
    0.87
     opioids
    0.87
     salaried
    0.86
     Cabrio
    0.86
    ‟
    0.86
     Park
    0.85
    POSITIVE LOGITS
    STOCK
    0.82
    YEAR
    0.80
    :])
    0.73
    tzmann
    0.73
    dut
    0.73
    WITH
    0.71
    dum
    0.70
    lə
    0.69
    SHOT
    0.68
    ILLS
    0.68
    Act Density 0.000%

    No Known Activations