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

    Neuronpedia

    INDEX
    Explanations

    references to variable definitions and assignments in programming code

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

    code related symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.78
    SourceChecksum
    -0.77
    出版年
    -0.74
    Jîn
    -0.71
    +#+#
    -0.71
    Vidite
    -0.71
    ReusableCell
    -0.71
    MemoryWarning
    -0.69
     <<<<<<<<<<<<<<
    -0.69
    хьтан
    -0.69
    POSITIVE LOGITS
    =(
    0.47
    =(-
    0.35
    =
    0.35
     part
    0.32
    }=(
    0.31
    =((
    0.31
    ↵
    0.30
     |=
    0.29
     Levi
    0.29
    bo
    0.29
    Act Density 0.016%

    No Known Activations