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

    Neuronpedia

    INDEX
    Explanations

    statements of fact or existence using forms of "to be" such as "is", "'s", "be", and "are"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     abstraction
    -0.07
    ç¦ģ
    -0.06
     prim
    -0.06
    /cms
    -0.06
     Dynam
    -0.06
    ÑģÑı
    -0.06
    vik
    -0.06
     prem
    -0.06
    Ä°
    -0.06
     deb
    -0.06
    POSITIVE LOGITS
    ays
    0.07
     Zot
    0.06
     truly
    0.06
    thetic
    0.06
    иÑĩа
    0.06
    isel
    0.06
    εÏģο
    0.06
    iversary
    0.06
     byste
    0.06
    ÑĮко
    0.06
    Act Density 0.174%

    No Known Activations