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

    Neuronpedia

    INDEX
    Explanations

    overall sentiment or emotional tone in content

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

    programming language syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Хьажоргаш
    -0.73
     Numerade
    -0.64
    mbggenerated
    -0.59
    IBOutlet
    -0.59
    Tembelea
    -0.57
     katholischen
    -0.56
    enumi
    -0.56
    HomeAsUpEnabled
    -0.56
    elemField
    -0.54
    ondissement
    -0.53
    POSITIVE LOGITS
    0.82
    <bos>
    0.64
    Gri
    0.48
     the
    0.47
    })();

    0.46
    )

    0.45
    Tur
    0.45
    Du
    0.45
    }));

    0.45
     Wra
    0.44
    Act Density 0.017%
    No Known Activations