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

    Neuronpedia

    INDEX
    Explanations

    bodies of water

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     canh
    -0.07
     conferences
    -0.07
     disbelief
    -0.07
     Nagar
    -0.06
     ----------------------------------------------------------------------------
    -0.06
    라이
    -0.06
     sites
    -0.06
    είς
    -0.06
    �
    -0.06
     relay
    -0.06
    POSITIVE LOGITS
     gebru
    0.07
    єм
    0.07
    .fill
    0.06
    матрива
    0.06
     معل
    0.06
    byss
    0.06
     explodes
    0.06
    DataManager
    0.06
    =Math
    0.06
    -tra
    0.06
    Act Density 0.056%

    No Known Activations