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

    Neuronpedia

    INDEX
    Explanations

    states of being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     craziness
    0.15
    ↵
    0.15
     如果
    0.15
     싶은
    0.14
     które
    0.14
     ovens
    0.14
    czas
    0.13
     welches
    0.13
     Maybe
    0.13
     lassen
    0.13
    POSITIVE LOGITS
     able
    0.28
     aware
    0.27
     engaged
    0.26
     willing
    0.24
     unwilling
    0.24
     involved
    0.24
     adept
    0.23
     reluctant
    0.23
     embroiled
    0.22
     preoccupied
    0.21
    Act Density 0.109%

    No Known Activations