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

    Neuronpedia

    INDEX
    Explanations

    sections that indicate a significant event or outcome

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

    Text following a question mark

    np_acts-logits-general · gemini-2.0-flash

    Q:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    basicConfig
    -0.67
    })*/
    -0.67
    <bos>
    -0.64
     [],
    -0.61
    %%
    -0.61
    "]
    -0.58
    */
    -0.58
    ]]
    -0.57
    (),
    -0.56
     {},
    -0.55
    POSITIVE LOGITS
    ">//
    0.75
     estekak
    0.69
     fides
    0.63
    なお
    0.60
     Shoulders
    0.59
     Bonus
    0.58
     متعلقه
    0.57
     referenties
    0.56
     StringTokenizer
    0.54
    cticide
    0.54
    Act Density 0.058%

    No Known Activations