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

    Neuronpedia

    INDEX
    Explanations

    Code/file snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EDURE
    -0.07
    ячи
    -0.07
     fos
    -0.07
     Parliament
    -0.06
     pParent
    -0.06
    ("-");↵
    -0.06
     İz
    -0.06
     unite
    -0.06
    setData
    -0.06
    _TER
    -0.06
    POSITIVE LOGITS
    _Row
    0.06
     Madame
    0.06
    .kotlin
    0.06
    Mutable
    0.06
     lệ
    0.06
     integrate
    0.06
     ทอง
    0.06
    		↵	↵
    0.06
    -syntax
    0.06
     Hawaiian
    0.06
    Act Density 0.007%

    No Known Activations