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

    Neuronpedia

    INDEX
    Explanations

    this example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Trit
    0.43
     Pops
    0.40
    ίας
    0.40
    nosed
    0.40
    ην
    0.39
     Lust
    0.39
     Constru
    0.39
     Clements
    0.39
     revisit
    0.39
    tuned
    0.39
    POSITIVE LOGITS
    ↓
    0.54
    например
    0.50
     இன்னொரு
    0.48
    Вот
    0.45
     ниже
    0.45
     Например
    0.44
     كله
    0.43
     http
    0.43
     注意
    0.43
     şekilde
    0.43
    Act Density 0.054%

    No Known Activations