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

    Neuronpedia

    INDEX
    Explanations

    structured text related to file paths and URLs

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

    defining paths and objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.95
    |}{$
    -0.79
    "])
    -0.77
    '):
    -0.74
    ///</
    -0.73
    ]),
    -0.72
    _));
    -0.71
    %"),
    -0.71
    '))
    -0.69
    ++)
    -0.69
    POSITIVE LOGITS
    _
    0.58
    ForRow
    0.54
    )
    0.50
    [,
    0.47
    BindingResult
    0.47
    ^
    0.46
    ([...
    0.46
    Scénario
    0.46
    stí
    0.46
     piele
    0.45
    Act Density 0.255%

    No Known Activations