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

    Neuronpedia

    INDEX
    Explanations

    fragments related to programming and data handling

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

    data retrieval and processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -1.07
     queſta
    -1.00
    iſen
    -0.98
    ロウィン
    -0.96
    <unused43>
    -0.95
    <unused41>
    -0.95
    <unused74>
    -0.95
    <unused14>
    -0.95
    <unused79>
    -0.95
    <pad>
    -0.94
    POSITIVE LOGITS
    ↵↵
    0.45
    !
    0.42
    <eos>
    0.42
    ,
    0.40
    ?
    0.38
    ↵
    0.38
    .
    0.38
    0
    0.36
    1
    0.36
    3
    0.36
    Act Density 0.012%

    No Known Activations