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

    Neuronpedia

    INDEX
    Explanations

    names, titles, and affiliations of people

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NSCoder
    -1.23
     snippetHide
    -1.16
     defaultstate
    -1.11
    rungsseite
    -1.09
    TagMode
    -1.07
     Normdatei
    -0.98
     >=",
    -0.98
     propOrder
    -0.98
    __*/
    -0.98
    mybatisplus
    -0.98
    POSITIVE LOGITS
     inner
    0.54
     
    0.54
     a
    0.53
     general
    0.53
     ed
    0.51
     No
    0.50
     co
    0.50
     social
    0.49
     H
    0.48
     head
    0.48
    Act Density 1.839%

    No Known Activations