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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Burning
    -0.07
    Favorite
    -0.06
    mousemove
    -0.06
     suburbs
    -0.06
    '*
    -0.06
     Kindle
    -0.06
     �
    -0.06
    th
    -0.06
    _CR
    -0.06
    _compile
    -0.06
    POSITIVE LOGITS
    (dl
    0.07
    211
    0.07
     blanco
    0.06
    ісля
    0.06
    .src
    0.06
     dlouho
    0.06
     having
    0.06
    味
    0.06
    �
    0.06
    Cách
    0.06
    Act Density 0.007%

    No Known Activations