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

    Neuronpedia

    INDEX
    Explanations

    code snippets and parts of computer programs

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -2.13
    '
    -0.57
    ']){
    -0.51
    ↵
    -0.49
    __':
    -0.49
    ’
    -0.46
     conosco
    -0.45
    RegressionTest
    -0.45
    [toxicity=0]
    -0.45
    AddHtmlAttribute
    -0.44
    POSITIVE LOGITS
    errHandler
    0.79
    WebElementEntity
    0.65
    quests
    0.63
     CreateTagHelper
    0.60
     Vikipedi
    0.60
    odotus
    0.59
    ientôt
    0.56
    ttino
    0.56
    ertion
    0.53
    wiss
    0.52
    Act Density 10.028%

    No Known Activations