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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to programming and data structures

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

    board games, communication systems, data format, packing fraction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aang
    -0.42
    ↵↵
    -0.40
    て
    -0.35
     follow
    -0.32
        
    -0.32
    <?
    -0.32
     transfer
    -0.32
    Donald
    -0.31
     зв
    -0.31
    ром
    -0.30
    POSITIVE LOGITS
     estekak
    0.76
     تضيفلها
    0.73
    0.71
    adpleegd
    0.68
     виправивши
    0.67
    __":
    0.66
    migrationBuilder
    0.66
     ModelExpression
    0.65
    __':
    0.65
     Normdatei
    0.63
    Act Density 0.178%

    No Known Activations