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

    Neuronpedia

    INDEX
    Explanations

    Code and software development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ]).
    -0.07
     thro
    -0.07
     clandest
    -0.06
     Workbook
    -0.06
    contro
    -0.06
    ="",
    -0.06
    }},↵
    -0.06
    aravel
    -0.06
     upro
    -0.06
     Vendor
    -0.06
    POSITIVE LOGITS
    iert
    0.07
     Headers
    0.07
    Classifier
    0.07
    Month
    0.06
    ILLE
    0.06
    ‰
    0.06
    _Params
    0.06
    .extract
    0.06
    HeaderCode
    0.06
     rin
    0.06
    Act Density 0.000%

    No Known Activations