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

    Neuronpedia

    INDEX
    Explanations

    adverbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    إ
    -0.07
    “They
    -0.06
    тися
    -0.06
    aea
    -0.06
    ческих
    -0.06
    	AM
    -0.06
    "They
    -0.06
     
    -0.06
    ออ
    -0.06
    -_
    -0.06
    POSITIVE LOGITS
     stereotype
    0.07
     trat
    0.06
    suz
    0.06
    heritance
    0.06
    uture
    0.06
     ao
    0.06
     toDate
    0.06
    iments
    0.06
    _decode
    0.06
     illusion
    0.06
    Act Density 0.121%

    No Known Activations