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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trav
    -0.07
     StringUtil
    -0.07
     köş
    -0.06
    SUR
    -0.06
    附近
    -0.06
     recursos
    -0.06
     prize
    -0.06
    XI
    -0.06
     Winner
    -0.06
    ursos
    -0.06
    POSITIVE LOGITS
    ======
    0.07
    edes
    0.07
     syncing
    0.07
    (prediction
    0.07
     precios
    0.06
    <::
    0.06
    />
    0.06
    iei
    0.06
    แนะ
    0.06
     نخست
    0.06
    Act Density 0.000%

    No Known Activations