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

    Neuronpedia

    INDEX
    Explanations

    studies and findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Presumably
    0.45
     ఉండే
    0.43
     ترقی
    0.43
     असतो
    0.43
     Ensures
    0.41
     Colonies
    0.41
    属于
    0.41
    viving
    0.41
    专属
    0.40
     относятся
    0.40
    POSITIVE LOGITS
     concluded
    1.15
     conclude
    1.03
     concludes
    1.01
     findings
    0.98
    CONCLUS
    0.97
     conclud
    0.97
     निष्कर्ष
    0.95
     conclusion
    0.93
    Conclusions
    0.93
    conclusion
    0.92
    Act Density 0.031%

    No Known Activations