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

    Neuronpedia

    INDEX
    Explanations

    bit more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )=>
    1.21
    tart
    1.16
    cbc
    1.15
    nk
    1.13
    mst
    1.12
     cnv
    1.08
     nhưng
    1.07
    npc
    1.06
    entures
    1.06
    png
    1.06
    POSITIVE LOGITS
    .¹
    1.30
     upravo
    1.29
    !”.
    1.24
    .”
    1.23
    ’!
    1.21
    .“
    1.20
    .</
    1.20
    !”
    1.17
     justamente
    1.16
     саме
    1.16
    Act Density 1.320%

    No Known Activations