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

    Neuronpedia

    INDEX
    Explanations

    introducing examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    srand
    1.70
     sett
    1.69
    璜
    1.61
     obliv
    1.61
    HING
    1.58
    Влади
    1.57
    pulsewidth
    1.57
     eikä
    1.54
     Как
    1.53
     مرت
    1.53
    POSITIVE LOGITS
    ार
    1.82
     cataly
    1.57
    tions
    1.54
    น
    1.51
    во
    1.50
    اً
    1.50
    وفر
    1.49
    1.48
    но
    1.46
    lardan
    1.45
    Act Density 0.392%

    No Known Activations