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

    Neuronpedia

    INDEX
    Explanations

    pronunciation explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.67
     people
    0.64
     att
    0.64
     lost
    0.63
     (
    0.63
     act
    0.61
     over
    0.60
     sent
    0.60
     all
    0.58
     breaking
    0.58
    POSITIVE LOGITS
    ̐
    0.74
    ੲ
    0.74
    Arduino
    0.73
    ‌ర
    0.72
    Neon
    0.71
    TreeMap
    0.71
    Pumpkin
    0.70
    MYSQL
    0.70
    ७
    0.69
    Mutex
    0.69
    Act Density 0.101%

    No Known Activations