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

    Neuronpedia

    INDEX
    Explanations

    punctuation and whitespace character patterns within code blocks

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

    Code snippets ending with curly brackets and parentheses

    np_acts-logits-general · gemini-2.0-flash

    closing braces and parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -1.01
    клопе
    -0.89
    DockStyle
    -0.83
    OGND
    -0.79
    PreferredItem
    -0.78
    IBOutlet
    -0.77
    MigrationBuilder
    -0.73
     invokingState
    -0.73
    دانشنامهٔ
    -0.72
    <_>
    -0.70
    POSITIVE LOGITS
    </tr>
    0.60
     }
    0.51
    }})
    0.51
    )})
    0.47
     )}
    0.46
    </tbody>
    0.45
     });
    0.45
    }},
    0.45
    }}/>
    0.45
    }
    0.43
    Act Density 0.102%

    No Known Activations