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

    Neuronpedia

    INDEX
    Explanations

    HTML header tags and structural elements related to document organization

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

    method and constructor summaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]);
    -0.45
    BagConstraints
    -0.45
    "]);
    -0.42
     metav
    -0.38
    IsMutable
    -0.37
    ")]
    -0.37
    ]");
    -0.37
    ](
    -0.35
    ]);
    -0.35
    </s>
    -0.35
    POSITIVE LOGITS
    </h3>
    1.66
    '}>
    0.74
    '},
    0.73
    '},
    0.67
    }';
    0.67
    '};
    0.66
    </i>
    0.65
    '}
    0.63
    </h4>
    0.62
    .';
    0.62
    Act Density 0.002%

    No Known Activations