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

    Neuronpedia

    INDEX
    Explanations

    growth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cramped
    -0.08
    倉
    -0.07
     Aus
    -0.07
    .cr
    -0.07
     Lei
    -0.06
     Oz
    -0.06
    凌
    -0.06
     张
    -0.06
    احة
    -0.06
    anus
    -0.06
    POSITIVE LOGITS
     performance
    0.07
     dokonce
    0.07
    tokenizer
    0.07
    (ep
    0.07
    -speed
    0.06
    sburgh
    0.06
    ?>"><
    0.06
     hasNext
    0.06
     Performance
    0.06
     respir
    0.06
    Act Density 0.002%

    No Known Activations