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

    Neuronpedia

    INDEX
    Explanations

    foreign words and acronyms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     komunik
    -0.07
     Kuala
    -0.07
    _cons
    -0.07
     Ja
    -0.06
    OVE
    -0.06
    �
    -0.06
     comparative
    -0.06
     Buyer
    -0.06
    シュ
    -0.06
     canada
    -0.06
    POSITIVE LOGITS
     Cadillac
    0.07
     UBND
    0.06
     월세
    0.06
     CRC
    0.06
     anh
    0.06
     salope
    0.06
    PTR
    0.06
    APON
    0.06
    achment
    0.06
     Іван
    0.06
    Act Density 0.005%

    No Known Activations