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

    Neuronpedia

    INDEX
    Explanations

    state of being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    podr
    -1.23
     selalu
    -1.20
    vägen
    -1.19
    mittag
    -1.18
     POSSIBLE
    -1.16
    ܘ
    -1.14
     siempre
    -1.13
     and
    -1.13
    atisfaction
    -1.11
    strahlung
    -1.11
    POSITIVE LOGITS
     about
    1.76
     still
    1.66
     able
    1.55
     too
    1.54
     now
    1.45
     so
    1.38
     wearing
    1.35
     glad
    1.34
     not
    1.32
     then
    1.30
    Act Density 0.032%

    No Known Activations