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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    The neuron detects license‐header boilerplate in source files, i.e. comment lines containing copyright and GNU license notices.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     pnl
    -0.07
    يني
    -0.06
    τηση
    -0.06
    RH
    -0.06
     výstav
    -0.06
     Jackson
    -0.06
    ớm
    -0.06
     cinsel
    -0.06
     Mormons
    -0.06
    _feature
    -0.06
    POSITIVE LOGITS
    ]=$
    0.07
    */↵↵
    0.07
    );}↵
    0.07
    	
↵
↵
    0.07
    _delegate
    0.06
     },
↵
↵
    0.06
     ],
↵
    0.06
    )'],↵
    0.06
    紀
    0.06
    .basename
    0.06
    Act Density 0.012%

    No Known Activations