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

    Neuronpedia

    INDEX
    Explanations

    responsible for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     title
    0.40
    imble
    0.40
    mounted
    0.39
    ಟಕ
    0.38
    izable
    0.38
    suspended
    0.37
    title
    0.37
    omed
    0.37
     stool
    0.36
    ospheric
    0.36
    POSITIVE LOGITS
     позд
    0.44
    🧑
    0.43
     लॉगिन
    0.41
    !!!");
    0.41
     লঙ্ঘ
    0.41
     largos
    0.40
    侔
    0.40
     djel
    0.40
     связанных
    0.40
     فره
    0.39
    Act Density 0.000%

    No Known Activations