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

    Neuronpedia

    INDEX
    Explanations

    code snippets with URLs and regular expressions

    oai_token-act-pair · gemini-2.0-flash

    url

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    url
    -2.30
     url
    -2.13
    URL
    -1.95
    Url
    -1.87
     URL
    -1.84
     Url
    -1.63
     URLs
    -1.51
    urls
    -1.49
     urls
    -1.41
    URLs
    -1.24
    POSITIVE LOGITS
    rrggbb
    0.76
     mukana
    0.64
     setPrice
    0.58
     Efq
    0.54
    ^(@)
    0.54
    {#
    0.54
     airbag
    0.53
     uſed
    0.52
     endfor
    0.51
     jäsen
    0.51
    Act Density 0.872%

    No Known Activations