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

    Neuronpedia

    INDEX
    Explanations

    nested documents, source art

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    淡
    0.52
    巡
    0.46
    Additional
    0.44
    影
    0.44
    RP
    0.43
    Alic
    0.43
    敏
    0.43
    nard
    0.43
    server
    0.42
    不存在
    0.41
    POSITIVE LOGITS
     enveloping
    0.50
     św
    0.47
     préf
    0.47
    ladı
    0.46
     hati
    0.46
     tucked
    0.46
     detonation
    0.46
    ër
    0.45
     blockage
    0.45
    attho
    0.45
    Act Density 0.003%

    No Known Activations