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

    Neuronpedia

    INDEX
    Explanations

    functions and their definitions or invocations

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

    file operation variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الحياه
    -0.68
    __":
    -0.63
     ſein
    -0.62
    elebr
    -0.62
    GenerationType
    -0.61
     CreateTagHelper
    -0.61
     незавершена
    -0.61
    Tembelea
    -0.60
    XmlAccessType
    -0.60
     ་་
    -0.60
    POSITIVE LOGITS
     p
    0.74
     r
    0.72
    R
    0.71
     b
    0.70
     m
    0.69
     s
    0.69
     g
    0.66
    M
    0.66
     c
    0.65
     R
    0.63
    Act Density 1.125%

    No Known Activations