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

    Neuronpedia

    INDEX
    Explanations

    city names and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Untersuchung
    0.44
     учащихся
    0.41
     Untersuchungen
    0.40
    氘
    0.40
     সুস্পষ্ট
    0.39
    डेट
    0.39
    栾
    0.39
     setToDefault
    0.38
    Examination
    0.38
    硅
    0.37
    POSITIVE LOGITS
     Croydon
    0.47
     Bournemouth
    0.46
    tingham
    0.46
    ley
    0.44
    on
    0.44
    2
    0.44
    es
    0.43
    less
    0.43
    field
    0.43
    ford
    0.43
    Act Density 0.000%

    No Known Activations