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

    Neuronpedia

    INDEX
    Explanations

    lists of categories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ten
    -0.07
    ện
    -0.07
    Week
    -0.07
     entertaining
    -0.07
     beings
    -0.06
     current
    -0.06
     bribery
    -0.06
     cabinets
    -0.06
    تون
    -0.06
     Weeks
    -0.06
    POSITIVE LOGITS
     ""){↵
    0.06
    conut
    0.06
     "'.
    0.06
    ())))↵
    0.06
    !!}↵
    0.06
    $criteria
    0.06
    Framework
    0.06
    ]={
    0.06
     Smash
    0.06
     Vince
    0.06
    Act Density 0.014%

    No Known Activations