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

    Neuronpedia

    INDEX
    Explanations

    various structural components related to code or programming syntax

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

    Tokens appearing before "and"

    np_acts-logits-general · gemini-2.0-flash

    lists of numbers and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <>
    -0.60
    Hentet
    -0.57
     שוליים
    -0.56
    日閲覧
    -0.56
    \{\\
    -0.55
     HomeComponent
    -0.51
    satunya
    -0.51
    رشف
    -0.51
     <<<<<<<<<<<<<<
    -0.51
     Trotzdem
    -0.50
    POSITIVE LOGITS
    respectively
    0.83
    bootstrapcdn
    0.79
     illetve
    0.73
    WriteAttribute
    0.68
    yntaxException
    0.66
     <=",
    0.64
     alike
    0.64
     suivants
    0.61
    worse
    0.59
     posteriores
    0.59
    Act Density 0.966%

    No Known Activations