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

    Neuronpedia

    INDEX
    Explanations

    order of events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     urlencode
    -0.07
    oter
    -0.07
    tığını
    -0.07
    “We
    -0.06
    상의
    -0.06
     northeastern
    -0.06
     sempre
    -0.06
    RestController
    -0.06
    _parm
    -0.06
    닥
    -0.06
    POSITIVE LOGITS
    atures
    0.07
    ATURE
    0.07
     useStyles
    0.06
     neighb
    0.06
    };↵↵
    0.06
    .ids
    0.06
    --)
    0.06
    ;
↵
↵
    0.06
    、​
    0.06
    ，然后
    0.06
    Act Density 0.059%

    No Known Activations