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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thấy
    -0.07
    (cx
    -0.07
     pacman
    -0.07
    _bit
    -0.06
    ວ
    -0.06
    できて
    -0.06
     Berkshire
    -0.06
     startTime
    -0.06
    到
    -0.06
     tie
    -0.06
    POSITIVE LOGITS
     Ruth
    0.08
    .Gen
    0.08
    _management
    0.07
    .Fore
    0.07
    _subject
    0.07
    _ajax
    0.07
    Eval
    0.07
     COLUMN
    0.07
    Groups
    0.07
    _EVT
    0.07
    Act Density 0.051%

    No Known Activations