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

    Neuronpedia

    INDEX
    Explanations

    Code and errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enge
    -0.06
     output
    -0.06
     ///↵
    -0.06
    _int
    -0.06
    ses
    -0.06
    érc
    -0.06
     ¦
    -0.06
     网
    -0.06
     Produkte
    -0.06
    -0.06
    POSITIVE LOGITS
    .green
    0.07
    天天
    0.07
     đọ
    0.07
     Lilly
    0.07
     domestically
    0.06
     nights
    0.06
    افت
    0.06
    (handle
    0.06
     pits
    0.06
     mapStateToProps
    0.06
    Act Density 0.000%

    No Known Activations