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

    Neuronpedia

    INDEX
    Explanations

    patterns related to defining functions and querying databases

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

    IQueryable one function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GenerationType
    -0.64
     CreateTagHelper
    -0.64
     للمعارف
    -0.63
    AndEndTag
    -0.58
    exitRule
    -0.58
     незавершена
    -0.57
    AndroidJUnit
    -0.55
    saraba
    -0.55
    сылкі
    -0.55
    ativement
    -0.55
    POSITIVE LOGITS
    (...
    1.51
     (...
    1.16
    (...)
    0.98
     (...)
    0.80
    (…)
    0.56
     ...
    0.56
     {...
    0.51
     "...
    0.46
    “...
    0.46
     (…)
    0.46
    Act Density 0.001%

    No Known Activations