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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     кра
    -0.06
     Govern
    -0.06
     автор
    -0.06
     Burlington
    -0.06
     xem
    -0.06
     Brittany
    -0.06
    ;background
    -0.06
    keiten
    -0.06
    'es
    -0.06
    起
    -0.06
    POSITIVE LOGITS
    _dec
    0.07
    _license
    0.07
     Isaac
    0.07
    abric
    0.07
     [<
    0.07
     "|"
    0.07
    (md
    0.06
    订单
    0.06
     piss
    0.06
    annah
    0.06
    Act Density 0.005%

    No Known Activations