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

    Neuronpedia

    INDEX
    Explanations

    references from fully scanned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಕ್‌
    0.41
     inventories
    0.38
     обстоя
    0.38
     backups
    0.38
     endowments
    0.37
     caloric
    0.36
    布団
    0.36
     acuerdos
    0.36
     circumst
    0.36
     Kuznet
    0.36
    POSITIVE LOGITS
     Perspective
    0.52
    ็บ
    0.51
     Happy
    0.44
    优化
    0.44
     만족
    0.42
    itley
    0.42
     চলেছে
    0.40
     реша
    0.39
     የበለጠ
    0.39
     stronger
    0.38
    Act Density 0.000%

    No Known Activations