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

    Neuronpedia

    INDEX
    Explanations

    phrases related to family and personal relationships

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

    celebrated, duties, branches sold

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.45
    ↵
    -0.44
    .
    -0.40
    <strong>
    -0.38
    <b>
    -0.35
    (
    -0.35
     currently
    -0.33
    。
    -0.32
    <em>
    -0.32
     
    -0.31
    POSITIVE LOGITS
    Datuak
    1.30
     autorytatywna
    1.20
    <unused52>
    1.11
    <unused41>
    1.11
     パンチラ
    1.11
    <unused79>
    1.11
    [@BOS@]
    1.11
    <unused16>
    1.10
    <unused8>
    1.10
    <pad>
    1.10
    Act Density 0.014%

    No Known Activations