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

    Neuronpedia

    INDEX
    Explanations

    comments and documentation indicators in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    comment delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.65
     dezelve
    -0.64
     plufieurs
    -0.57
     chrétien
    -0.53
    makeText
    -0.53
     Мексичка
    -0.51
    XmlRootElement
    -0.50
    colhead
    -0.50
     تضيفلها
    -0.50
     zijne
    -0.50
    POSITIVE LOGITS
    **/
    2.08
     **/
    1.66
    **/
    1.63
     **/
    1.38
    ****/
    1.34
    *****/
    1.33
    *********/
    1.33
    ***/
    1.32
    ******/
    1.25
    ***********/
    1.23
    Act Density 0.007%

    No Known Activations