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

    Neuronpedia

    INDEX
    Explanations

    whitespace characters or empty tokens

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

    headings and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الرياضيه
    -0.44
     Weeknd
    -0.43
    показания
    -0.42
    coglie
    -0.39
    caloosa
    -0.39
    fton
    -0.38
     indisponible
    -0.37
     Moors
    -0.37
    hasia
    -0.36
    paddingLeft
    -0.36
    POSITIVE LOGITS
    ​
    1.65
     ​
    1.30
    .​
    1.28
    )​
    1.27
    ,​
    1.25
    :​
    1.23
    ​,
    1.17
    ​.
    1.15
    $​
    1.06
    }$​
    0.99
    Act Density 0.007%

    No Known Activations