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

    Neuronpedia

    INDEX
    Explanations

    explanation of algorithms and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    科普
    0.43
    امه
    0.38
     географи
    0.38
    嚓
    0.38
    ূর
    0.38
     Syrup
    0.37
    Returns
    0.36
     সিরাপ
    0.36
    嗤
    0.36
    াম
    0.36
    POSITIVE LOGITS
     listed
    0.42
    ictive
    0.41
     build
    0.40
    álisis
    0.40
     &/
    0.40
     Miche
    0.40
    ifest
    0.39
    Miche
    0.38
     attributable
    0.38
    じて
    0.38
    Act Density 0.002%

    No Known Activations