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

    Neuronpedia

    INDEX
    Explanations

    examples or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    地元
    0.38
    buyer
    0.37
    citizen
    0.37
     headcount
    0.36
    total
    0.36
    paid
    0.35
    ometown
    0.35
    employee
    0.34
    citizens
    0.34
    venue
    0.34
    POSITIVE LOGITS
     bijvoorbeeld
    0.60
     sommige
    0.55
     moderne
    0.54
     modernes
    0.50
     beispielsweise
    0.50
     modernen
    0.49
     niektórych
    0.49
     misalnya
    0.48
     modern
    0.47
     například
    0.46
    Act Density 0.283%

    No Known Activations