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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -1.16
     Efq
    -1.15
     Monfieur
    -1.03
     auffi
    -1.02
     myſelf
    -0.97
    -0.93
     ―――――
    -0.92
     Houſe
    -0.91
     дописавши
    -0.91
    />";
    -0.91
    POSITIVE LOGITS
    .
    0.59
    ↵↵
    0.58
    ,
    0.57
     in
    0.56
     (
    0.54
    e
    0.52
     
    0.52
    ↵
    0.51
    the
    0.51
    x
    0.49
    Act Density 0.047%

    No Known Activations