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

    Neuronpedia

    INDEX
    Explanations

    numbers, entities, and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mer
    0.62
    dir
    0.52
    u
    0.52
    iz
    0.50
    ar
    0.49
    ang
    0.49
    log
    0.49
    inter
    0.49
    ef
    0.48
    display
    0.47
    POSITIVE LOGITS
     नगरपालिका
    0.50
     towns
    0.48
     ferries
    0.47
     commuters
    0.46
     parishes
    0.46
    ப்பட்டுள்ள
    0.46
     महीना
    0.46
     iconography
    0.46
     Vietnamese
    0.45
     paddy
    0.45
    Act Density 0.000%

    No Known Activations