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

    Neuronpedia

    INDEX
    Explanations

    Bird, novelty, factors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ike
    0.41
    ba
    0.38
    ractive
    0.37
    ero
    0.37
    onn
    0.37
    পিড
    0.37
    icidal
    0.37
     e
    0.36
    iv
    0.36
    ٹ
    0.36
    POSITIVE LOGITS
     സ്ത്ര
    0.45
     přest
    0.41
    聂
    0.40
     സ്ഥ
    0.40
    各类
    0.39
     الخلق
    0.39
    设计的
    0.38
    过度
    0.38
     appearances
    0.38
     ස්ථා
    0.38
    Act Density 0.000%

    No Known Activations