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

    Neuronpedia

    INDEX
    Explanations

    official actions and regulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Warhammer
    0.41
     අතර
    0.40
    编辑器
    0.40
     описы
    0.39
     extremadamente
    0.39
     rì
    0.38
     Очень
    0.38
    日本では
    0.38
     दशक
    0.37
    经历了
    0.37
    POSITIVE LOGITS
     raffle
    0.52
     ambulances
    0.50
     affidavits
    0.49
     licenses
    0.48
     foolproof
    0.48
     grievance
    0.48
     publicity
    0.48
     inspections
    0.47
     officials
    0.47
     allotted
    0.47
    Act Density 0.011%

    No Known Activations