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

    Neuronpedia

    INDEX
    Explanations

    quality, nature, property

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Speech
    0.43
    λον
    0.39
     immig
    0.37
    asketball
    0.37
    ড়াই
    0.37
     کاروبار
    0.36
    ᾷ
    0.36
     Speech
    0.36
    уго
    0.36
     документы
    0.35
    POSITIVE LOGITS
    性質
    1.27
     nature
    1.27
    性质
    1.25
    nature
    1.16
     Nature
    1.11
     sifat
    1.09
     NATURE
    1.09
    Nature
    1.06
     tính
    0.98
     naturaleza
    0.96
    Act Density 0.004%

    No Known Activations