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

    Neuronpedia

    INDEX
    Explanations

    records

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ap
    0.44
    or
    0.41
    ce
    0.41
    Answer
    0.40
    VIP
    0.40
    avoid
    0.40
     politely
    0.40
    be
    0.39
    uest
    0.38
    stop
    0.38
    POSITIVE LOGITS
     records
    1.01
     RECORDS
    0.91
     Records
    0.90
    records
    0.80
    Records
    0.79
    记录
    0.59
     রেকর্ড
    0.57
     записи
    0.54
    レコード
    0.54
     registros
    0.52
    Act Density 0.000%

    No Known Activations