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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	model
    -0.07
     Fallen
    -0.07
     out
    -0.07
     également
    -0.07
     chosen
    -0.06
    だと
    -0.06
    reaction
    -0.06
     lui
    -0.06
    ные
    -0.06
    out
    -0.06
    POSITIVE LOGITS
     delimiter
    0.06
     dedi
    0.06
     dispers
    0.06
    -Con
    0.06
     بهتر
    0.06
     durations
    0.06
    ités
    0.06
     تقس
    0.06
     Greenville
    0.06
    اساس
    0.06
    Act Density 0.016%

    No Known Activations