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

    Neuronpedia

    INDEX
    Explanations

    questions

    oai_token-act-pair · gemini-2.0-flash

    where

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.94
    complexContent
    -0.88
     betweenstory
    -0.86
    expandindo
    -0.81
    tagHelperRunner
    -0.77
    setVerticalGroup
    -0.75
    modelBuilder
    -0.73
     Roskov
    -0.73
    ніципалі
    -0.73
    couvrez
    -0.70
    POSITIVE LOGITS
    ajoz
    0.48
    ?
    0.46
    ?*
    0.45
    Rhestr
    0.42
    verlag
    0.41
     &_
    0.40
    っそ
    0.40
    pur
    0.39
    pen
    0.39
    บ้าง
    0.39
    Act Density 1.165%

    No Known Activations