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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    entario
    -0.06
    eca
    -0.06
     Tes
    -0.06
    lük
    -0.06
    ibal
    -0.06
    EZ
    -0.06
    stackpath
    -0.06
     iterating
    -0.06
    alls
    -0.06
    abet
    -0.06
    POSITIVE LOGITS
     warnings
    0.07
    IN
    0.07
     differences
    0.07
     nữ
    0.06
    =T
    0.06
    .GetAsync
    0.06
     reminder
    0.06
     ↵
    0.06
     grievances
    0.06
    gain
    0.06
    Act Density 0.000%

    No Known Activations