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

    Neuronpedia

    INDEX
    Explanations

    Wind, Fire, and Wonder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    raries
    -0.07
     geile
    -0.07
    	Optional
    -0.07
     chess
    -0.06
     tensors
    -0.06
     Joshua
    -0.06
     deltas
    -0.06
     GetEnumerator
    -0.06
    公路
    -0.06
     dispatcher
    -0.06
    POSITIVE LOGITS
     yarn
    0.07
    ://'
    0.07
    553
    0.06
    Highlight
    0.06
     prints
    0.06
    ライン
    0.06
     nghề
    0.06
     faithful
    0.06
    akit
    0.06
     Commod
    0.06
    Act Density 0.018%

    No Known Activations