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

    Neuronpedia

    INDEX
    Explanations

    structured programming elements, particularly related to configuration settings in code

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

    Equals sign followed by a number

    np_acts-logits-general · gemini-2.0-flash

    cam or PHYREG based

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.93
     مرئيه
    -0.81
     CreateTagHelper
    -0.73
     للاسماء
    -0.71
     CURIAM
    -0.71
     betweenstory
    -0.71
     surla
    -0.68
    MessageTagHelper
    -0.68
     BrowserModule
    -0.65
    tanleria
    -0.64
    POSITIVE LOGITS
     '
    0.38
     code
    0.37
     
    0.36
     universal
    0.32
    code
    0.32
     "
    0.30
     beast
    0.30
     meaning
    0.30
     differentiate
    0.29
    string
    0.29
    Act Density 0.827%

    No Known Activations