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

    Neuronpedia

    INDEX
    Explanations

    method definitions in programming context

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

    Code snippets and code-related syntax

    np_acts-logits-general · gemini-2.0-flash

    connect function or std library call

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tvguidetime
    -1.03
     autorytatywna
    -0.90
    )";
    -0.90
     Мексичка
    -0.90
    Tikang
    -0.87
    ]));
    -0.85
    ']))
    -0.81
     nahilalakip
    -0.80
    '):
    -0.78
    }))
    -0.78
    POSITIVE LOGITS
     ...
    1.29
    </code>
    1.21
    ...
    1.20
    (...)
    1.10
    ....
    1.08
     ....
    1.07
    [...]
    1.02
     …
    1.02
     [...]
    1.02
    …
    0.99
    Act Density 0.725%

    No Known Activations