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

    Neuronpedia

    INDEX
    Explanations

    instances of tab characters in the text

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

    table references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ers
    -0.50
    ьаж
    -0.49
    __":
    -0.45
    prices
    -0.43
     Willi
    -0.43
    Willi
    -0.42
    extrême
    -0.42
    increase
    -0.41
    er
    -0.40
    Ɓ
    -0.40
    POSITIVE LOGITS
    tab
    2.41
     tab
    1.52
    TAB
    1.18
    tabs
    1.13
     tabs
    1.11
    tabl
    1.07
     TAB
    1.06
    tabli
    1.05
    タブ
    0.97
    addTab
    0.95
    Act Density 0.014%

    No Known Activations