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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    似
    -0.06
    овых
    -0.06
    Cont
    -0.06
     силь
    -0.06
    ※
    -0.06
    --------------------------------------------------------------------------↵
    -0.06
    默认
    -0.06
     NES
    -0.06
     Lig
    -0.06
    greens
    -0.06
    POSITIVE LOGITS
     داستان
    0.07
    asn
    0.07
    aret
    0.07
    τιο
    0.06
     meetup
    0.06
     Dynamo
    0.06
     superb
    0.06
    rowCount
    0.06
     Warren
    0.06
     Chic
    0.06
    Act Density 0.001%

    No Known Activations