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

    Neuronpedia

    INDEX
    Explanations

    Code processing JSON data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    啦
    -0.07
     anticip
    -0.07
    hci
    -0.07
    Overview
    -0.07
    ew
    -0.06
     sembl
    -0.06
    Csv
    -0.06
    _POP
    -0.06
    े�
    -0.06
    AP
    -0.06
    POSITIVE LOGITS
     확실
    0.07
    -catching
    0.06
     обличчя
    0.06
    .prof
    0.06
    etik
    0.06
    .actions
    0.06
    녕
    0.06
    gett
    0.06
    द
    0.06
     duplication
    0.06
    Act Density 0.004%

    No Known Activations