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

    Neuronpedia

    INDEX
    Explanations

    how things look or sound

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     feelings
    1.27
     ощущения
    1.07
     Seems
    1.06
     érz
    1.06
     gevoel
    1.02
     느껴
    1.01
     perceiving
    1.00
    feeling
    0.99
     atmosphere
    0.98
     комфор
    0.98
    POSITIVE LOGITS
     bytecode
    1.07
    𝑝
    1.05
    𝑖
    1.02
    ндә
    0.99
     SPS
    0.94
     SMS
    0.91
    𝑑
    0.90
    𝑒
    0.89
    Notify
    0.88
     fool
    0.87
    Act Density 0.063%

    No Known Activations