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

    Neuronpedia

    INDEX
    Explanations

    surnames in citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ucksack
    0.21
     Draco
    0.20
     Ecusson
    0.19
     Chihuahua
    0.19
    ggbb
    0.19
    🚕
    0.18
    gdock
    0.18
     गाली
    0.18
     selben
    0.17
     Gecko
    0.17
    POSITIVE LOGITS
     and
    0.21
    in
    0.19
     /
    0.19
    V
    0.19
    у
    0.19
     for
    0.19
    L
    0.19
    re
    0.18
    ag
    0.18
     (
    0.18
    Act Density 0.010%

    No Known Activations