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

    Neuronpedia

    INDEX
    Explanations

    commas and periods

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ^(@)
    -1.41
    IUrlHelper
    -1.29
     Efq
    -1.27
    NUMX
    -1.23
     समीक्षक
    -1.15
    principalColumn
    -1.11
    iffance
    -1.11
     snippetHide
    -1.10
    Czytaj
    -1.10
    mybatisplus
    -1.10
    POSITIVE LOGITS
    ↵↵
    1.22
    ↵
    1.16
    <eos>
    0.92
      
    0.87
    ,
    0.85
    !
    0.79
    ?
    0.78
     (
    0.76
                                   
    0.73
    en
    0.73
    Act Density 2.151%

    No Known Activations