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

    Neuronpedia

    INDEX
    Explanations

    component that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     their
    0.41
     aby
    0.41
     Misalnya
    0.40
     Such
    0.40
     these
    0.40
     <$>
    0.39
     saranno
    0.39
     त्यांच्या
    0.38
    一个个
    0.38
     soient
    0.38
    POSITIVE LOGITS
     whose
    0.88
     comprised
    0.87
     cuyo
    0.81
     cuya
    0.79
    whose
    0.79
     consisting
    0.78
     called
    0.77
     composed
    0.73
     cuyos
    0.73
     जिसमें
    0.71
    Act Density 0.988%

    No Known Activations