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

    Neuronpedia

    INDEX
    Explanations

    ** ` [ ] { } `

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     другому
    0.41
     автомат
    0.40
     stát
    0.40
    स्थल
    0.39
     жало
    0.39
    葶
    0.39
     राज्य
    0.39
     समायोजित
    0.39
    鱉
    0.39
     откло
    0.38
    POSITIVE LOGITS
     were
    0.45
     :
    0.43
     లు
    0.42
     $:
    0.42
    および
    0.42
    $:
    0.42
    াঃ
    0.41
    s
    0.40
     respectivos
    0.38
     Fonts
    0.38
    Act Density 0.073%

    No Known Activations