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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks indicating the end of lists or groupings

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

    ).toBe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fromString
    -0.42
     Zwiebel
    -0.41
     Madura
    -0.40
     Depreciation
    -0.40
    könig
    -0.40
     ustedes
    -0.39
    rasco
    -0.39
    URIComponent
    -0.39
    fileInfo
    -0.39
    styleable
    -0.38
    POSITIVE LOGITS
     ],
    1.66
     ),
    1.14
     ),
    1.13
     ].
    1.05
     ];
    0.96
     ]);
    0.95
     ).
    0.93
     ]:
    0.91
     []),
    0.84
     "),
    0.83
    Act Density 0.010%

    No Known Activations