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

    Neuronpedia

    INDEX
    Explanations

    examples or instances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    र्यंत
    0.41
    velles
    0.40
    ানোর
    0.39
    FARE
    0.39
    ased
    0.38
     seafood
    0.38
     meds
    0.38
     hadn
    0.38
     Native
    0.37
    ELSE
    0.37
    POSITIVE LOGITS
     مثلا
    0.52
     например
    0.49
    iPhone
    0.49
     misalnya
    0.47
    例えば
    0.47
    например
    0.46
     Örneğin
    0.46
     bijvoorbeeld
    0.45
     například
    0.45
     beispielsweise
    0.45
    Act Density 0.145%

    No Known Activations