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

    Neuronpedia

    INDEX
    Explanations

    Reflexive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gado
    -0.07
    ικ
    -0.06
     ceremonial
    -0.06
     nude
    -0.06
     робіт
    -0.06
    url
    -0.06
    离
    -0.06
     describe
    -0.06
    getTitle
    -0.06
    udicots
    -0.06
    POSITIVE LOGITS
    ease
    0.07
    233
    0.07
     Trouble
    0.07
    .SE
    0.07
    _Ass
    0.07
    -ever
    0.06
     MAIL
    0.06
     mathematical
    0.06
     конс
    0.06
     past
    0.06
    Act Density 0.011%

    No Known Activations