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

    Neuronpedia

    INDEX
    Explanations

    logs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     пок
    -0.08
    ่อต
    -0.07
     trải
    -0.06
    ComboBox
    -0.06
     Chevy
    -0.06
    -enabled
    -0.06
     equivalents
    -0.06
     Flowers
    -0.06
     opinions
    -0.06
     Mann
    -0.06
    POSITIVE LOGITS
     修
    0.06
    олет
    0.06
    (:,
    0.06
    (INT
    0.06
    fail
    0.06
    )]);↵
    0.06
     aerospace
    0.06
     rahatsız
    0.06
    電話
    0.06
    ])-
    0.06
    Act Density 0.025%

    No Known Activations