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
    或其他
    0.25
    ويم
    0.24
    韵
    0.24
    вающих
    0.23
    或者
    0.22
     अथवा
    0.22
    λαμβ
    0.22
     আমর
    0.22
     имају
    0.22
     yǐ
    0.22
    POSITIVE LOGITS
     picky
    0.35
     arrogant
    0.34
     stubborn
    0.33
     good
    0.32
     clueless
    0.32
     happy
    0.31
     joking
    0.30
     jobless
    0.29
     kidding
    0.29
     kind
    0.29
    Act Density 0.312%

    No Known Activations