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

    Neuronpedia

    INDEX
    Explanations

    Admiral, Acceleration, Hardware

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    también
    1.25
    er
    1.17
    ន្ថ
    1.08
    áf
    1.04
    ৌম
    1.02
    ッと
    1.02
    doctorId
    1.00
     recoge
    0.99
    OnChange
    0.98
    relsen
    0.97
    POSITIVE LOGITS
    >')
    1.01
    スーパー
    1.00
    al
    0.99
     perspici
    0.97
     Hardware
    0.96
    >',
    0.96
    ма
    0.95
    ിക്കും
    0.95
     степени
    0.95
     oluşan
    0.95
    Act Density 0.000%

    No Known Activations