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

    Neuronpedia

    INDEX
    Explanations

    model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     było
    -0.07
     التط
    -0.07
    unts
    -0.06
    _rates
    -0.06
     alles
    -0.06
     Liste
    -0.06
    exemple
    -0.06
    etat
    -0.06
    裡面
    -0.06
    روب
    -0.06
    POSITIVE LOGITS
    医师
    0.08
    ߣ
    0.07
     credential
    0.07
    三等奖
    0.07
     centralized
    0.07
     department
    0.07
    ducted
    0.06
    manifest
    0.06
    秉持
    0.06
     MLP
    0.06
    Act Density 0.031%

    No Known Activations