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

    Neuronpedia

    INDEX
    Explanations

    file paths in a specific format

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

    quoted paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MANN
    -0.41
    </sub>
    -0.41
    mann
    -0.41
    </em>
    -0.40
     hän
    -0.39
    Bibliografia
    -0.38
     financiera
    -0.38
     AppCompatTheme
    -0.37
    knex
    -0.37
    Note
    -0.36
    POSITIVE LOGITS
    ("/
    0.96
     "/
    0.94
    ="/
    0.91
    ('/
    0.87
    +'/
    0.82
     '/
    0.81
     @"/
    0.81
     `/
    0.80
    #!/
    0.77
    ={`/
    0.77
    Act Density 0.015%

    No Known Activations