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

    Neuronpedia

    INDEX
    Explanations

    October dates in submission documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ierra
    0.38
     girl
    0.38
     older
    0.37
     mulch
    0.36
     allergy
    0.36
     jewels
    0.36
     คะ
    0.35
     blows
    0.35
     moat
    0.35
    girl
    0.34
    POSITIVE LOGITS
     draft
    0.70
     Draft
    0.64
    Draft
    0.62
    draft
    0.59
    日期
    0.59
     제출
    0.57
     drafts
    0.57
     manuscript
    0.56
    submit
    0.55
     submission
    0.55
    Act Density 0.004%

    No Known Activations