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

    Neuronpedia

    INDEX
    Explanations

    code, technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bán
    -0.07
     主
    -0.06
     MatSnackBar
    -0.06
     Rank
    -0.06
    dling
    -0.06
    _calls
    -0.06
    .persist
    -0.06
    ιά
    -0.06
    .notifications
    -0.06
     pulls
    -0.06
    POSITIVE LOGITS
     {\↵
    0.07
    ,Th
    0.06
    ">'.$
    0.06
    lerimiz
    0.06
    IN
    0.06
    رفته
    0.06
    orning
    0.06
    {o
    0.06
    LEMENT
    0.06
    最后
    0.06
    Act Density 0.000%

    No Known Activations