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

    Neuronpedia

    INDEX
    Explanations

    references to Django backend models and configurations

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

    Python imports

    np_acts-logits-general · gemini-2.0-flash

    python import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ?),
    -1.05
    ?).
    -0.88
    ?");
    -0.86
    !);
    -0.85
    ?)
    -0.84
    !),
    -0.83
    !');
    -0.80
     []);
    -0.78
    .);
    -0.77
    ),
    -0.77
    POSITIVE LOGITS
     import
    1.92
     Import
    0.92
     imports
    0.79
     importing
    0.77
    </b>
    0.75
     impor
    0.73
     importation
    0.69
     IMPORT
    0.68
     importers
    0.67
    DebuggerNonUser
    0.67
    Act Density 0.041%

    No Known Activations