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

    Neuronpedia

    INDEX
    Explanations

    meaningful order and cells

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ktron
    0.48
    joon
    0.46
    ars
    0.46
    age
    0.44
     माप
    0.43
    ark
    0.43
    itud
    0.43
    pkins
    0.42
    iguation
    0.41
     талант
    0.41
    POSITIVE LOGITS
    ݨ
    0.47
    i
    0.47
    Ком
    0.47
    CSR
    0.46
     rije
    0.44
    ดอก
    0.44
    Пер
    0.44
    ПР
    0.44
     smach
    0.44
     緊急
    0.44
    Act Density 0.000%

    No Known Activations