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

    Neuronpedia

    INDEX
    Explanations

    Code with commas/indentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ¤
    -0.07
    _categorical
    -0.07
     foll
    -0.07
    王
    -0.06
     unravel
    -0.06
    (mp
    -0.06
    رض
    -0.06
    ars
    -0.06
    ges
    -0.06
    _cat
    -0.06
    POSITIVE LOGITS
    τολ
    0.07
    _LOG
    0.06
     сдел
    0.06
    .indent
    0.06
     Logger
    0.06
     asia
    0.06
    .VisualBasic
    0.06
    Invoice
    0.05
    ."},↵
    0.05
    Serialize
    0.05
    Act Density 0.001%

    No Known Activations