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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kidd
    -0.07
    (Camera
    -0.06
    Checkpoint
    -0.06
    ilight
    -0.06
    ازي
    -0.06
     Temp
    -0.06
    (bucket
    -0.06
    7
    -0.06
     Jefferson
    -0.06
     souvent
    -0.06
    POSITIVE LOGITS
     respects
    0.07
     outlines
    0.07
     나는
    0.06
     partie
    0.06
     fourth
    0.06
    .zeros
    0.06
    �
    0.06
     barang
    0.06
     INTER
    0.06
    }')
    0.06
    Act Density 0.582%

    No Known Activations