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

    Neuronpedia

    INDEX
    Explanations

    remote

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     currentIndex
    -0.07
     rent
    -0.07
    .Tr
    -0.07
    -files
    -0.06
     rules
    -0.06
     금
    -0.06
     certified
    -0.06
     signalling
    -0.06
    -category
    -0.06
    qt
    -0.06
    POSITIVE LOGITS
    dio
    0.07
    ENCH
    0.07
     باست
    0.07
    dsn
    0.07
     FUN
    0.06
    оці
    0.06
    IND
    0.06
    OWN
    0.06
     nation
    0.06
     forgiven
    0.06
    Act Density 0.008%

    No Known Activations