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

    Neuronpedia

    INDEX
    Explanations

    Math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <fieldset
    -0.07
     ارشد
    -0.07
    DataType
    -0.07
    雷
    -0.07
     лиц
    -0.06
    contributors
    -0.06
    PostalCodesNL
    -0.06
     whom
    -0.06
     aku
    -0.06
     процед
    -0.06
    POSITIVE LOGITS
    RegularExpression
    0.07
     Woman
    0.06
    '].'</
    0.06
    Themes
    0.06
    VPN
    0.06
     penetrated
    0.06
    ><?
    0.05
     entrances
    0.05
    ]$
    0.05
    겠습니다
    0.05
    Act Density 0.011%

    No Known Activations