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

    Neuronpedia

    INDEX
    Explanations

    evaluating specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    觉得
    0.44
    }}^{*}
    0.41
     деше
    0.40
     在
    0.40
    ב
    0.40
    회사
    0.39
    覺得
    0.39
    或者
    0.39
    大
    0.39
     இன்
    0.39
    POSITIVE LOGITS
    ပြု
    0.45
     amendments
    0.42
     conduct
    0.42
     hurricanes
    0.42
     discretion
    0.42
     barista
    0.42
     Fermat
    0.42
     militari
    0.41
     lessen
    0.41
     umožňuje
    0.40
    Act Density 0.001%

    No Known Activations