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

    Neuronpedia

    INDEX
    Explanations

    Node.js module imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ക്കാല
    0.42
    Ⲕ
    0.38
     ඔබ
    0.37
    empl
    0.37
    ruari
    0.37
    вершена
    0.37
    hatikan
    0.37
    櫚
    0.37
     मद्देन
    0.36
    בוה
    0.36
    POSITIVE LOGITS
     =
    0.39
     ضمن
    0.36
     модуль
    0.36
     회사
    0.36
    rds
    0.36
     modul
    0.34
     :=
    0.34
    Pkg
    0.34
    elfare
    0.34
     संधी
    0.34
    Act Density 0.003%

    No Known Activations