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

    Neuronpedia

    INDEX
    Explanations

    elements related to data structures and programming syntax

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

    enclosed in parentheses

    np_acts-logits-general · gemini-2.0-flash

    terms followed by parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $_"
    -0.82
    CppCodeGen
    -0.81
     Houſe
    -0.75
     Jefus
    -0.75
     Efq
    -0.74
    ſelf
    -0.71
     myſelf
    -0.71
     Anſ
    -0.70
     photolibrary
    -0.70
     "\<
    -0.67
    POSITIVE LOGITS
     (
    2.30
    (
    1.67
    （
    1.42
     [
    1.09
     ("
    1.05
     （
    1.04
     ($
    1.01
     ('
    0.98
     (“
    0.97
     $(
    0.96
    Act Density 1.029%

    No Known Activations