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

    Neuronpedia

    INDEX
    Explanations

    managing and distributing procedures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     절대
    1.20
     큰
    1.20
     반드시
    1.18
     받아
    1.16
     자주
    1.14
     größere
    1.14
     항상
    1.14
     wszel
    1.11
     이해
    1.11
     Notable
    1.09
    POSITIVE LOGITS
    8
    1.12
    7
    1.12
    9
    1.12
    6
    1.10
    4
    1.09
    5
    1.07
    3
    0.99
    1
    0.91
    President
    0.90
    ovember
    0.90
    Act Density 0.121%

    No Known Activations