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

    Neuronpedia

    INDEX
    Explanations

    create, Stack, Slice, Host, cluster

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    า
    1.18
     After
    1.09
    ش
    1.09
     eigent
    1.08
    մբ
    1.07
     Suddenly
    1.06
     Should
    1.02
     Overall
    1.02
     But
    1.02
     April
    1.02
    POSITIVE LOGITS
    l
    1.34
    w
    1.34
    r
    1.12
    room
    1.10
    Catalogue
    1.09
    k
    1.09
    istique
    1.07
    ad
    1.05
    Harvard
    1.05
    Mineral
    1.05
    Act Density 0.001%

    No Known Activations