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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marriott
    -0.07
     Ко
    -0.06
    ryption
    -0.06
     bit
    -0.06
     thesis
    -0.06
    $scope
    -0.06
     Slee
    -0.06
     Fragment
    -0.06
     ступ
    -0.06
     buddy
    -0.06
    POSITIVE LOGITS
    instein
    0.07
    ाहत
    0.06
    702
    0.06
     digestive
    0.06
    ieve
    0.06
    突
    0.06
    _DEVICES
    0.06
     nella
    0.06
    -content
    0.06
     同
    0.06
    Act Density 0.001%

    No Known Activations