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

    Neuronpedia

    INDEX
    Explanations

    blocks of code in programming syntax

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

    Code-related tokens and syntax

    np_acts-logits-general · gemini-2.0-flash

    cubic centimeter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebServlet
    -0.67
     GenerationType
    -0.64
    agisse
    -0.62
    دانشنامهٔ
    -0.61
    %;
    -0.60
     off
    -0.58
     prof
    -0.58
    <>
    -0.55
     sa
    -0.55
     =
    -0.53
    POSITIVE LOGITS
    }
    1.20
    )
    0.95
    </
    0.91
    </tr>
    0.90
    }.
    0.88
    </tbody>
    0.86
    }`).
    0.85
    ]
    0.84
    });
    0.83
    }).
    0.83
    Act Density 0.062%

    No Known Activations