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

    Neuronpedia

    INDEX
    Explanations

    the word "for"

    oai_token-act-pair · gemini-2.0-flash

    specific place names or proper nouns

    np_token-act-pair-logits · gpt-4o-mini

    nonsensical/random text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cplusplus
    -0.50
     ModelExpression
    -0.49
    SpringBootTest
    -0.48
     بيها
    -0.47
     ThemeData
    -0.47
    HasKey
    -0.46
    \|_{\
    -0.45
    \|_{
    -0.45
    copyWith
    -0.45
    %@",
    -0.44
    POSITIVE LOGITS
     Meksiku
    0.81
     AssemblyCulture
    0.68
    Pfalz
    0.68
    цездатний
    0.68
     étrangère
    0.62
     otomatig
    0.59
    RenderAtEndOf
    0.58
    CodedInputStream
    0.57
     AllMovie
    0.56
    setVerticalGroup
    0.56
    Act Density 0.314%

    No Known Activations