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

    Neuronpedia

    INDEX
    Explanations

    referencing sections and steps by number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ब्रिटिश
    0.30
    ড়ো
    0.30
    screwdriver
    0.29
    डेजा
    0.29
    धारण
    0.28
    কিছু
    0.28
    anía
    0.28
    ່ວນ
    0.28
    níci
    0.28
    悹
    0.28
    POSITIVE LOGITS
     IV
    0.43
    ４
    0.40
     fifth
    0.40
     II
    0.39
    ㉖
    0.39
     sixth
    0.39
     III
    0.38
     ১৩
    0.38
     ४
    0.38
     VI
    0.38
    Act Density 0.038%

    No Known Activations