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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting elements within the text

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

    closing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IBOutlet
    -0.65
    Хьажоргаш
    -0.60
    HomeAsUpEnabled
    -0.52
     يتيمه
    -0.51
     katholischen
    -0.51
    eridge
    -0.48
     esternos
    -0.48
    enumi
    -0.48
        
    -0.47
    ApiOperation
    -0.45
    POSITIVE LOGITS
    0.83
    })();

    0.60
    <bos>
    0.60
    })*/
    0.55
    )}

    0.54
    

    0.53
    ]),

    0.52
    }));

    0.51
     braço
    0.50
    ")));

    0.50
    Act Density 0.013%
    No Known Activations