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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    |h
    -0.06
    lland
    -0.06
    ario
    -0.06
     languages
    -0.06
    ówn
    -0.06
     illnesses
    -0.06
    审
    -0.06
    .Euler
    -0.06
    AGO
    -0.06
     июля
    -0.06
    POSITIVE LOGITS
     /\.
    0.07
    Much
    0.06
     인터넷
    0.06
     офици
    0.06
     Bei
    0.06
     dout
    0.06
    _CAN
    0.06
    Joseph
    0.06
    Mark
    0.06
    ustainable
    0.06
    Act Density 0.134%

    No Known Activations