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

    Neuronpedia

    INDEX
    Explanations

    override safety protocols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     финансо
    0.45
    的企业
    0.41
    财务
    0.40
    投资者
    0.40
     Unternehmer
    0.39
     компании
    0.39
     компания
    0.38
     économique
    0.37
    👔
    0.36
    企业家
    0.36
    POSITIVE LOGITS
     lesions
    0.44
     radiographs
    0.43
     edema
    0.43
     lesion
    0.43
     ectopic
    0.39
     staining
    0.39
     inactivation
    0.38
     etiology
    0.38
     supernatant
    0.38
     fetal
    0.38
    Act Density 0.001%

    No Known Activations