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

    Neuronpedia

    INDEX
    Explanations

    news articles referring to a number of cases

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uml
    -0.07
     Mercer
    -0.07
     MPL
    -0.07
    pany
    -0.07
    γÏī
    -0.06
    elas
    -0.06
    merc
    -0.06
    esi
    -0.06
    è¬
    -0.06
    PELL
    -0.06
    POSITIVE LOGITS
     CBS
    0.14
    CBS
    0.13
    BS
    0.08
     CB
    0.08
    CB
    0.07
     Paramount
    0.07
    adge
    0.07
     kolo
    0.07
    antz
    0.07
    bs
    0.07
    Act Density 0.007%

    No Known Activations