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

    Neuronpedia

    INDEX
    Explanations

    domains and practices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deleter
    0.31
     Factory
    0.31
     calcium
    0.30
     Screen
    0.30
    给
    0.30
     medically
    0.30
     förm
    0.30
    朝鲜
    0.30
    اشة
    0.29
     Crypto
    0.29
    POSITIVE LOGITS
    practices
    0.47
    गारी
    0.44
    goals
    0.43
    markers
    0.41
    改革
    0.39
     reforms
    0.39
    ps
    0.38
     теория
    0.38
    leaders
    0.38
     процессы
    0.38
    Act Density 0.225%

    No Known Activations