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

    Neuronpedia

    INDEX
    Explanations

    enumerated lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    qu
    -0.07
    utors
    -0.07
    .defer
    -0.07
     enthusiasts
    -0.07
    QU
    -0.07
    .ErrorMessage
    -0.06
    _trip
    -0.06
     т
    -0.06
    _driver
    -0.06
    _TYPE
    -0.06
    POSITIVE LOGITS
     Sidney
    0.07
     On
    0.06
    PerPage
    0.06
     capitalist
    0.06
    烈
    0.06
    0.06
    !!}↵
    0.06
    onDelete
    0.06
    !';↵
    0.06
     Al
    0.06
    Act Density 0.021%

    No Known Activations