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

    Neuronpedia

    INDEX
    Explanations

    okay let's break down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ცია
    0.44
     دارید
    0.43
     expecting
    0.40
     وانت
    0.39
    шому
    0.39
     armon
    0.38
     youre
    0.38
     assumes
    0.37
     बेसिकली
    0.37
     erwart
    0.36
    POSITIVE LOGITS
     lets
    1.65
     let
    1.48
     Lets
    1.43
    Lets
    1.39
     Let
    1.35
     vamos
    1.34
    Let
    1.33
     Давайте
    1.28
     давайте
    1.25
     Vamos
    1.20
    Act Density 0.048%

    No Known Activations