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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     condemn
    -0.09
    那是
    -0.07
    介
    -0.07
     negot
    -0.07
     responder
    -0.07
    itizen
    -0.07
     jealousy
    -0.07
    蚕
    -0.07
    たり
    -0.07
    .Completed
    -0.07
    POSITIVE LOGITS
    .Return
    0.07
    (parts
    0.07
     Fi
    0.06
     trips
    0.06
     Additional
    0.06
    Pagination
    0.06
     latest
    0.06
    CFG
    0.06
     daily
    0.06
    不忘初心
    0.06
    Act Density 0.274%

    No Known Activations