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

    Neuronpedia

    INDEX
    Explanations

    google books URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    电商
    -0.08
    faculty
    -0.07
    beh
    -0.07
    ;
↵
↵
↵
↵
    -0.07
    getc
    -0.07
    wish
    -0.07
    icipation
    -0.07
    人参
    -0.07
    Board
    -0.07
    ↵
↵
↵
↵
    -0.07
    POSITIVE LOGITS
    _rhs
    0.07
     לישראל
    0.07
     waving
    0.06
     Diesel
    0.06
    ():↵
    0.06
     xlink
    0.06
    (QL
    0.06
    ROID
    0.06
     removed
    0.06
    _RESOLUTION
    0.06
    Act Density 0.001%

    No Known Activations