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

    Neuronpedia

    INDEX
    Explanations

    the titles, subtitles, and section headings in technical papers

    oai_token-act-pair · gemini-2.0-flash

    discussion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.72
    ècie
    -0.70
    LabelTagHelper
    -0.60
    istoitu
    -0.59
    httphttps
    -0.59
    ɵɵelementStart
    -0.56
    ⓧ
    -0.54
     gyhoeddwyd
    -0.53
    BufferException
    -0.53
    ADUATE
    -0.52
    POSITIVE LOGITS
    <bos>
    0.75
    parsedMessage
    0.60
     estimés
    0.57
     beginnetje
    0.55
     ſch
    0.54
     ſy
    0.53
     Alsace
    0.52
     ſtre
    0.52
     Infórmanos
    0.52
     eventdata
    0.52
    Act Density 1.896%

    No Known Activations