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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /fs
    -0.07
     cấp
    -0.06
     vững
    -0.06
    defaults
    -0.06
     된
    -0.06
     달
    -0.06
     tránh
    -0.06
    授
    -0.06
    提出
    -0.06
    (ns
    -0.06
    POSITIVE LOGITS
    elenium
    0.07
     риз
    0.06
    ISK
    0.06
    γνω
    0.06
     powering
    0.06
    мерикан
    0.06
     Amelia
    0.06
    同時
    0.06
     Ale
    0.06
     Περ
    0.06
    Act Density 0.094%

    No Known Activations