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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .br
    -0.07
     treaties
    -0.06
    CHAIN
    -0.06
     Bitcoin
    -0.06
     BREAK
    -0.06
    gp
    -0.06
    اوي
    -0.06
    균
    -0.06
    $rows
    -0.06
     Brno
    -0.06
    POSITIVE LOGITS
    _A
    0.07
    _WP
    0.06
     parliament
    0.06
    .Rule
    0.06
     window
    0.06
    _q
    0.06
     airing
    0.06
     ham
    0.06
    ._↵
    0.06
    ，用
    0.06
    Act Density 0.000%

    No Known Activations