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

    Neuronpedia

    INDEX
    Explanations

    Book of Revelation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    one
    0.54
    cut
    0.50
    and
    0.48
     acquisitions
    0.45
    backed
    0.44
    一家
    0.43
    ick
    0.42
    enee
    0.42
    inching
    0.42
     cut
    0.41
    POSITIVE LOGITS
     Algunos
    0.50
     LocalDateTime
    0.48
     ylabel
    0.46
     Medication
    0.46
    嶼
    0.45
    DomainMask
    0.45
     problemática
    0.45
     Alguns
    0.45
     问题
    0.45
     Medications
    0.44
    Act Density 0.002%

    No Known Activations